Systems, methods, and computer-readable media for characterizing microspheric material

A system comprising:

• at least one system configured to:
• receive image data representative of a microscopic image of a sample microspheric material;
• segment the image data into a plurality of spatially-contiguous image regions;
• classify, by a trained machine-learning model, each of the plurality of spatially-contiguous image regions as corresponding to one of:
• a particle,
• an intra-particle pore, or
• an inter-particle void;
• and
• characterize the porosity of the microspheric material based on at least one of:
• a count of the intra-particle pores;
• an area of the intra-particle pores;
• an equivalent diameter of the intra-particle pores;
• or
• a pore-area fraction of the intra-particle pores.

A non-transitory computer readable medium comprising:

• a computer program code segment used to receive image data representative of a microscopic image of a sample microspheric material;
• a computer program code segment used to segment the image data into a plurality of spatially-contiguous image regions;
• a computer program code segment used to classify, by a trained machine-learning model, each of the plurality of spatially-contiguous image regions as corresponding to one of:
• a particle,
• an intra-particle pore, or
• an inter-particle void;
• and
• a computer program code segment used to characterize the porosity of the microspheric material based on at least one of:
• a count of the intra-particle pores;
• an area of the intra-particle pores;
• an equivalent diameter of the intra-particle pores;
• or
• a pore-area fraction of the intra-particle pores.