A Tensor Regularized Approach to Spatio-Temporal Pollutant Cartography Applied to Working Environments

Advancements in indoor pollutant sensor networks have revolutionized spatio-temporal cartography, making it an essential tool for evaluating and preventing pollution exposure risks in occupational environments. In this study, we introduce a novel spatio-temporal cartography technique that leverages the inherent smoothness of gas diffusion concentrations in both space and time. Our approach explicitly accounts for the temporal coherence and non-negativity of pollutant concentration maps, resulting in more interpretable estimates. We demonstrate the efficacy of our approach using real carbon dioxide (CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>) data collected during experiments at the Institut National de Recherche et Sécurité (INRS) in Nancy.