5:30 PM - 5:45 PM
△ [9p-W321-14] Efficient estimation for red-zone in silicon wafers for solar cells using machine learning
Keywords:machine learning, mapping, experimental design
Mapping measurement to find the spatial distribution of physical quantity by changing the measurement position on the sample surface is a fundamental material evaluation method.
Usually it's mapped with lattice-like coordinates, but also inefficient measurement points
for the purpose of measurement are included in that case.
Therefore, we aimed to obtain more probable physical quantity distribution from fewer measurement points.
In this study, we used LSE to efficiently estimate the boundary position for carrier lifetime mapping of silicon for solar cells, and estimated the low quality region.
Usually it's mapped with lattice-like coordinates, but also inefficient measurement points
for the purpose of measurement are included in that case.
Therefore, we aimed to obtain more probable physical quantity distribution from fewer measurement points.
In this study, we used LSE to efficiently estimate the boundary position for carrier lifetime mapping of silicon for solar cells, and estimated the low quality region.