AUTHOR=Leichter Artem , Almeev Renat R. , Wittich Dennis , Beckmann Philipp , Rottensteiner Franz , Holtz Francois , Sester Monika 

TITLE=Automated Segmentation of Olivine Phenocrysts in a Volcanic Rock Thin Section Using a Fully Convolutional Neural Network

JOURNAL=Frontiers in Earth Science

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/earth-science/articles/10.3389/feart.2022.740638

DOI=10.3389/feart.2022.740638

ISSN=2296-6463

ABSTRACT=An example of automatic approach to characterize and interpret the textural and compositional characteristics of solids phases in thin sections using machine learning is presented. In our study, we focus on the characterization of olivine in volcanic rocks, which is a phase that is often chemically zoned with variable Mg/(Mg+Fe) ratios or mg#. As the olivine crystals represent only less than 10 vol.% of the volcanic rock, a  pre-processing step is necessary to automatically detect the phases of interest in the images on a pixel level, which is achieved using Deep Learning. A major contribution of the presented approach is to use back-scattered electron images to (1) automatically segment all olivine crystals present in the thin section, (2) determine quantitatively their mg#, and (3) identify different populations depending on zoning type (e.g., normal vs. reversal zoning) and textural characteristics (e.g., microlites vs. phenocrysts). 
The segmentation of the olivine crystals is implemented with a pretrained fully convolution neural network model with DeepLabV3 architecture. The model is trained to identify olivine crystals in back-scattered electron (BSE) images using automatically generated training data. The training data are generated automatically from images which can easily be created from X-Ray element maps. 
Once the olivines are identified in the BSE images, the relationship between BSE intensity value and mg# is determined using a simple regression based on a set of given microprobe measurements. This learned functional relationship can then be applied to all olivine pixels in the whole data set. 
The paper describes the process in detail, shows analytical results and outlines the potential of this Deep Learning approach for petrological applications, resulting in the automatic characterization and interpretation of mineral textures and compositions with an unprecedented high resolution.