Siamese neural network improves the performance of a convolutional neural network in colloidal self-assembly state classification.

Identifying the state of the colloidal self-assembly process is critical to monitoring and controlling the system into desired configurations. Recent application of convolutional neural networks with unsupervised clustering has shown a comparable performance to conventional approaches, in representing and classifying the states of a simulated 2D colloidal batch assembly system. Despite the early success, capturing the subtle differences among similar configurations still presents a challenge.

Dopant-Free Hole-Transport Materials with Germanium Compounds Bearing Pseudohalide and Chalcogenide Moieties for Perovskite Solar Cells.

Hole-transport materials (HTMs) are key electronic components for the functioning of perovskite solar cells (PSCs) as they extract the photogenerated holes from the perovskite to be transported subsequently to the back electrode while minimizing the loss from electron recombination. Herein, we report the synthesis and characterization of novel germanium-based compounds with [{HC(CMeNAr)}GeNCS] (), [{HC(CMeNAr)}Ge(S)NCS] (), and [{HC(CMeNAr)}Ge(Se)NCS] () compositions, with Ar = 2,6-PrCH and the photovoltaic performance of and that is the same as for HTM in PSC. All compounds displayed excellent thermal properties and an appropriate alignment of energy levels for the perovskite with maximum optical absorption in the near-UV region.