Solid particle emissions from burning wood in three internal combustion biomass cooking stoves commonly used in southern Chile were compared. Each stove was used to show differences in sealing systems, combustion chamber shape, and heating surfaces in order to optimize biomass combustion and the energy produced at a low manufacturing cost. The influence of cooking stove design along with particle and gas emissions that resulted from the biomass combustion within the cooking stove was investigated in this study. Levels of diverse atmospheric contaminants, such as particulate matter, emission factor, NO_x, CO₂, and CO, and the temperature of the flue gases were determined with the Ch-28 method and UNE-EN 12815. The average emission of particulate matter was significantly reduced by modifying the geometry of the combustion chamber and heating surface of each stove, resulting in 5 g/h particle emissions in conventional equipment and 2 g/h in the improved equipment. In relation to gas emissions, there was a 25% maximum decrease in NO_x gases and 35% in CO after modifying the heating surface of each stove. This background supports the evidence of technological improvement with high environmental impact and low economic cost for local manufacturers.

Accurately predicting pollutant emission factors (EFs) from woody biomass fuels remains challenging because small-scale combustion tests are fuel-specific, time-consuming, and highly sensitive to operating conditions. This study combines controlled laboratory combustion experiments with a physics-informed artificial neural network (ANN–PINN) to estimate the emission factors of particulate matter (${\mathrm{EF}}_{PM}$), carbon monoxide (${\mathrm{EF}}_{CO}$), and nitrogen oxides (${\mathrm{EF}}_{NOx}$) using only laboratory-scale fuel characterization. Three pelletized woody biomass, Pinus radiata, Acacia dealbata, and Nothofagus obliqua, were analyzed through ultimate and proximate composition, lignin content, and TGA-derived parameters and tested in a residential pellet stove under identical control setpoints, resulting in a narrow and well-defined operating regime. A medium-depth ANN–PINN was constructed by integrating mechanistic constraints, monotonicity based on known emission trends and a weak carbon balance penalty, into a feed-forward neural network trained and evaluated using Leave-One-Out Cross-Validation. The model accurately reproduced the experimental behavior of ${\mathrm{EF}}_{CO}$ and captured structured variability in ${\mathrm{EF}}_{PM}$, while the limited nitrogen variability of the fuels restricted generalization for ${\mathrm{EF}}_{NOx}$. Sensitivities derived via automatic differentiation revealed physically coherent relationships, demonstrating that PM emissions depend jointly on fuel chemistry and aero-thermal conditions, CO emissions are dominated by mixing and temperature, and ${\mathrm{NO}}_x$ formation is primarily governed by fuel-bound nitrogen. When applied to external biomass fuels characterized independently in the literature, the ANN–PINN produced physically plausible predictions, highlighting its potential as a rapid, low-cost screening tool for assessing new biomass feedstocks and supporting cleaner residential heating technologies. The integrated experimental–PINN framework provides a physically consistent and data-efficient alternative to classical empirical correlations and purely data-driven ANN models.