COSMOS: A Data-Driven Probabilistic Time Series simulator for Chemical Plumes across Spatial Scales

TL;DR

COSMOS is a data-driven probabilistic model that efficiently generates realistic odor time series across large spatial scales, facilitating the development of odor navigation strategies without the high computational costs of CFD methods.

Contribution

It introduces COSMOS, a novel probabilistic framework that synthesizes realistic odor plumes from real data features, reducing computational load while maintaining key statistical properties.

Findings

COSMOS accurately reproduces odor statistics like whiff frequency and concentration.

Agents exposed to COSMOS and CFD plumes exhibit similar odor experiences and behaviors.

COSMOS enables large-scale odor simulation for environmental monitoring and navigation research.

Abstract

The development of robust odor navigation strategies for automated environmental monitoring applications requires realistic simulations of odor time series for agents moving across large spatial scales. Traditional approaches that rely on computational fluid dynamics (CFD) methods can capture the spatiotemporal dynamics of odor plumes, but are impractical for large-scale simulations due to their computational expense. On the other hand, puff-based simulations, although computationally tractable for large scales and capable of capturing the stochastic nature of plumes, fail to reproduce naturalistic odor statistics. Here, we present COSMOS (Configurable Odor Simulation Model over Scalable Spaces), a data-driven probabilistic framework that synthesizes realistic odor time series from spatial and temporal features of real datasets. COSMOS generates similar distributions of key statistical features such as whiff frequency, duration, and concentration as observed in real data, while dramatically reducing computational overhead. By reproducing critical statistical properties across a variety of flow regimes and scales, COSMOS enables the development and evaluation of agent-based navigation strategies with naturalistic odor experiences. To demonstrate its utility, we compare odor-tracking agents exposed to CFD-generated plumes versus COSMOS simulations, showing that both their odor experiences and resulting behaviors are quite similar.