Can deep learning extract useful information about energy dissipation and effective hydraulic conductivity from gridded conductivity fields?

Mohammad A. Moghaddam, Paul A.T. Ferre, Mohammad Reza Ehsani, Jeffrey Klakovich, Hoshin Vijay Gupta

Research output: Contribution to journalArticlepeer-review

Abstract

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.

Original languageEnglish (US)
Article number1668
JournalWater (Switzerland)
Volume13
Issue number12
DOIs
StatePublished - Jun 2 2021

Keywords

  • Centered kernel alignment
  • Deep learning
  • Effective hydraulic conductivity
  • Energy dissipation
  • Hidden layer representation
  • Hydrogeology
  • Machine learning
  • UNET

ASJC Scopus subject areas

  • Geography, Planning and Development
  • Biochemistry
  • Aquatic Science
  • Water Science and Technology

Fingerprint

Dive into the research topics of 'Can deep learning extract useful information about energy dissipation and effective hydraulic conductivity from gridded conductivity fields?'. Together they form a unique fingerprint.

Cite this