Project Overview

Airmen operating in extreme environments face physiological risks, including fatigue, cognitive decline, heat/cold stress, that current monitoring systems detection is too limited. This project is foundational research to develop a proof of concept a personalized AI "digital twin," a model trained on an individual's physiological data that forecasts health risks before they become critical, enabling proactive intervention rather than reactive treatment. A central hypothesis driving this work is that quantum-level biological phenomena offer earlier and more sensitive stress signals than conventional biomarkers. Part of this phenomena is biological photon emissions, ultraweak light produced as a byproduct of cellular metabolism whose intensity and coherence likely to reflect real-time cellular health and stress non-invasively. We will draw on publicly available datasets spanning physiology, genomics, proteomics, and quantum-level biological measurements to build a unified predictive model operating from the whole-body level deep down to the cellular, molecular level and atomic level.

Technical Goals

  1. Build a multi-scale data pipeline integrating wearable time-series data with molecular and quantum-level biomarkers (genomic, proteomic, biophoton emissions & biological quantum data)

  2. Simulate and optimize human physiological responses in extreme environments and explore quantum-based mechanisms of neural signaling (e.g., air & space force environment).

  3. Quantify whether quantum-level features (biophoton coherence, in particular) improve predictive performance over physiological baselines alone

  4. Design an intervention recommendation layer that translates predicted risk into actionable, personalized guidance

What We're Looking For

Recent graduate in computer science with interest in AI/ML and biological systems. Background in biology, physiology, or bioinformatics is a plus. The project has a foundational framework in place; the right candidate will drive proof-of-concept simple model implementation independently.

Clearance # AFRL-2026-1243

References:

M.E. Miller, E. Spatz, A unified view of a human digital twin, Hum.-Intell. Syst.Integr. 4 (2022) 23–33,

J. Lee, M. Azamfar, B. Bagheri, A unified digital twin framework for shop floordesign in industry 4.0 manufacturing systems, Manuf. Lett. 27 (2021) 87–91,

Ben Gaffinet, Jana Al Haj Ali, Yannick Naudet, and Hervé Panetto. Human Digital Twins: A systematic literature review and concept disambiguation for industry. Computers in Industry, Volume 166, April 2025, 104230

Corentin Ascone , and Frédéric Vanderhaegen. Towards a Holistic Framework for Digital Twins of Human-Machine Systems. IFAC, Volume 55, Issue 29, 2022,  67-72. https://doi.org/10.1016/j.ifacol.2022.10.233

citizenship

level

Additional Benefits

Awardees who reside more than 50 miles from their host laboratory and remain on tenure for at least six months are eligible for paid relocation to within the vicinity of their host laboratory.

A group health insurance program is available to awardees and their qualifying dependents in the United States.