Direct Multi-Modal Inversion of Geophysical Logs Using Deep Learning

Sergey Alyaev*, Ahmed H. Elsheikh

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

6 Citations (Scopus)
34 Downloads (Pure)


Geosteering of wells requires fast interpretation of geophysical logs which is a non-unique inverse problem. Current work presents a proof-of-concept approach to multi-modal probabilistic inversion of logs using a single evaluation of an artificial deep neural network (DNN). A mixture density DNN (MDN) is trained using the ”multiple-trajectory-prediction” loss functions, which avoids mode collapse typical for traditional MDNs, and allows multi-modal prediction ahead of data. The proposed approach is verified on the real-time stratigraphic inversion of gamma-ray logs. The multi-modal predictor outputs several likely inverse solutions/predictions, providing more accurate and realistic solutions compared to a deterministic regression using a DNN. For these likely stratigraphic curves, the model simultaneously predicts their probabilities, which are implicitly learned from the training geological data. The stratigraphy predictions and their probabilities obtained in milliseconds from the MDN can enable better real-time decisions under geological uncertainties.

Original languageEnglish
Article numbere2021EA002186
JournalEarth and Space Science
Issue number9
Publication statusPublished - 20 Sept 2022


  • deep neural network
  • geophysical inversion
  • mixture density network
  • multi-modal inversion
  • stratigraphic-based geosteering
  • well-log interpretation

ASJC Scopus subject areas

  • Environmental Science (miscellaneous)
  • General Earth and Planetary Sciences


Dive into the research topics of 'Direct Multi-Modal Inversion of Geophysical Logs Using Deep Learning'. Together they form a unique fingerprint.

Cite this