Skip to content
View drdmitrymikhaylov's full-sized avatar

Block or report drdmitrymikhaylov

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
drdmitrymikhaylov/README.md

Prof. Dr. Dmitry Mikhaylov

Physics AI Scientist · Professor · UN AI Research Expert Abu Dhabi, UAE

I build physics-informed AI systems that get deployed — not benchmarked and abandoned. My work puts physical laws inside the network: PINNs and physics-aware architectures applied to mineral exploration, agriculture, maritime operations, satellite earth observation, and neurotech.


Current

  • Director of Research Projects, Abu Dhabi Maritime Academy — AD Ports Group
  • Professor, Kyrgyz National University
  • AI Research Expert, United Nations (UNODC)
  • Co-founder & Chief Science Officer, DeepTech Engineering
  • Founder & CSO, Engiscent Pte. Ltd. (Singapore)

Research focus

Area What I work on
Physics-informed neural networks Industrial PINNs — solvers constrained by governing equations rather than data volume
Mineral & subsurface exploration Physics-aware inversion and prospectivity modelling
Agriculture Satellite and hyperspectral crop analytics; foundation models for agronomy
Maritime & port operations Underwater acoustics, surveillance, autonomous inspection
Earth observation Satellite imaging pipelines for monitoring and verification

Selected output

  • 116 publications on Google Scholar · 869 citations · h-index 13 · i10-index 15
  • ~30 international patents
  • 10 books and 3 coursebooks across 4 languages
  • Springer volume on PINNs for industrial applications (in progress)

Elsewhere

Pinned Loading

  1. making-pinns-work making-pinns-work Public

    A practical course on why physics-informed neural networks fail to converge — and what to do about it. Runnable notebooks on open benchmark problems.

    Jupyter Notebook

  2. navierpinn-mineral-ore-body-reconstruction navierpinn-mineral-ore-body-reconstruction Public

    Finding mineral ore bodies where nobody drilled. Physics-informed reconstruction that carries the equilibrium residual, so the model stays mechanically admissible between sparse drillholes. Patents…