Exposure to respirable coal mine dust (RCMD) can cause chronic and debilitating lung diseases. Real-time monitoring capabilities are sought which can enable a better understanding of dust components and sources. In many underground mines, RCMD includes three primary components which can be loosely associated with three major dust sources: coal dust from the coal seam itself, silicates from the surrounding rock strata, and carbonates from the inert ‘rock dust’ products that are applied to mitigate explosion hazards. A monitor which can reliably partition RCMD between these three components could thus allow source apportionment. And tracking silicates, specifically, could be valuable since the most serious health risks are typically associated with this component-particularly if abundant in crystalline silica. Envisioning a monitoring concept based on field microscopy, and following up on prior research using polarized light, the aim of the current study was to build and test a model to classify respirable-sized particles as either coal, silicates, or carbonates. For model development, composite dust samples were generated in the laboratory by successively depositing dust from high-purity materials onto a sticky transparent substrate, and imaging after each deposition event such that the identity of each particle was known a priori. Model testing followed a similar approach, except that real geologic materials were used as the source for each dust component. Results showed that the model had an overall accuracy of $$86.5\%$$
86.5
%
, indicating that a field-microscopy based monitor could support RCMD source apportionment and silicates tracking in some coal mines.