Gravity-Awareness: Deep Learning Models and LLM Simulation of Human Awareness in Altered Gravity

TL;DR

This paper introduces a dual computational framework combining physiological models and language-based simulations to understand human awareness and adaptation in various gravity conditions, from microgravity to hypergravity.

Contribution

It presents a novel integrated approach using machine learning and large language models to simulate and analyze human physiological and subjective responses to altered gravity environments.

Findings

Quantitative models accurately predict EEG and physiological changes across gravity levels.

Language model simulations produce introspective narratives consistent with physiological data.

Framework offers new insights into human adaptation in space-like conditions.

Abstract

Earth's gravity has fundamentally shaped human development by guiding the brain's integration of vestibular, visual, and proprioceptive inputs into an internal model of gravity: a dynamic neural representation enabling prediction and interpretation of gravitational forces. This work presents a dual computational framework to quantitatively model these adaptations. The first component is a lightweight Multi-Layer Perceptron (MLP) that predicts g-load-dependent changes in key electroencephalographic (EEG) frequency bands, representing the brain's cortical state. The second component utilizes a suite of independent Gaussian Processes (GPs) to model the body's broader physiological state, including Heart Rate Variability (HRV), Electrodermal Activity (EDA), and motor behavior. Both models were trained on data derived from a comprehensive review of parabolic flight literature, using published findings as anchor points to construct robust, continuous functions. To complement this quantitative analysis, we simulated subjective human experience under different gravitational loads, ranging from microgravity (0g) and partial gravity (Moon 0.17g, Mars 0.38g) to hypergravity associated with spacecraft launch and re-entry (1.8g), using a large language model (Claude 3.5 Sonnet). The model was prompted with physiological parameters to generate introspective narratives of alertness and self-awareness, which closely aligned with the quantitative findings from both the EEG and physiological models. This combined framework integrates quantitative physiological modeling with generative cognitive simulation, offering a novel approach to understanding and predicting human performance in altered gravity