Smell of Source: Learning-Based Odor Source Localization with Molecular Communication

Odor source localization is a fundamental challenge in molecular communication, environmental monitoring, disaster response, industrial safety, and robotics. In this study, we investigate three major approaches: Bayesian filtering, machine learning (ML) models, and physics-informed neural networks (PINNs) with the aim of odor source localization in a single-source, single-molecule case. By considering the source-sensor architecture as a transmitter-receiver model we explore source localization under the scope of molecular communication. Synthetic datasets are generated using a 2D advection-diffusion PDE solver to evaluate each method under varying conditions, including sensor noise and sparse measurements. Our experiments demonstrate that $\mathbf{\text{Physics-Informed}}\mathbf{\text{Neural}}\mathbf{\text{Networks}}\mathbf{\text{(PINNs)}}$ achieve the lowest localization error of $\mathbf{0.89}\times {\mathbf{10}}^{-\mathbf{6}}$ m, outperforming $\mathbf{\text{machine}}\mathbf{\text{learning}}\mathbf{\text{(ML)}}\mathbf{\text{inversion}}$ ($\mathbf{1.48}\times {\mathbf{10}}^{-\mathbf{6}}$ m) and $\mathbf{\text{Kalman}}\mathbf{\text{filtering}}$ ($\mathbf{1.62}\times {\mathbf{10}}^{-\mathbf{6}}$ m). The $\mathbf{\text{reinforcement}}\mathbf{\text{learning}}\mathbf{\text{(RL)}}$ approach, while achieving a localization error of $\mathbf{3.01}\times {\mathbf{10}}^{-\mathbf{6}}$ m, offers an inference time of $\mathbf{0.147}$ s, highlighting the trade-off between accuracy and computational efficiency among different methodologies.