Unsupervised neural-implicit laser absorption tomography for quantitative imaging of unsteady flames

This paper presents a novel neural-implicit approach to laser absorption tomography (LAT) with an experimental demonstration. A coordinate neural network is used to represent thermochemical state variables as continuous functions of space and time. Unlike most existing neural methods for LAT, which rely on prior simulations and supervised training, our approach is based solely on LAT measurements, utilizing a differentiable observation operator with line parameters provided in a standard spectroscopy database format. Although reconstructing scalar fields from multi-beam absorbance data is an inherently ill-posed, nonlinear inverse problem, our continuous space–time parameterization supports physics-inspired regularization strategies and enables data assimilation. Synthetic and experimental tests are conducted to validate the method, demonstrating robust performance and reproducibility. We show that our neural-implicit approach to LAT can capture the dominant spatial modes of unsteady flames from very sparse measurement data, indicating its potential to reveal combustion instabilities in measurement domains with minimal optical access.

Novelty and Significance Statement

Industrial environments, such as gas turbine test beds, present significant diagnostic challenges due to harsh operating conditions and limited optical access. In this work, we demonstrate the first long-time-horizon reconstructions of simultaneous 2D temperature and water vapor mole fraction fields in laboratory burners using neural-implicit laser absorption tomography (NILAT). We characterize NILAT’s performance through a synthetic phantom study featuring a realistic mean profile, broadband fluctuations, and tonal dynamics, highlighting its robustness and reconstruction accuracy. We also validate the applicability of established regularization parameter selection methods. This sensing framework extends beyond controlled laboratory conditions and offers potential for deployment in extreme environments where direct measurements are impractical.