6 Materialchemie
Filtern
Erscheinungsjahr
- 2021 (2) (entfernen)
Dokumenttyp
- Zeitschriftenartikel (2) (entfernen)
Sprache
- Englisch (2)
Referierte Publikation
- ja (2)
Schlagworte
- Advanced material (1)
- Artificial intelligence (1)
- Automated image analysis (1)
- Electron microscopy (1)
- Image segmentation (1)
- Neural networks (1)
- Quantum dots (1)
- Quantum yield (1)
- Solar concentrator (1)
- Solar energy (1)
Organisationseinheit der BAM
- 1.2 Biophotonik (2) (entfernen)
Paper des Monats
- ja (1)
Luminescent solar concentrators (LSC) allow to obtain renewable energy from building integrated photovoltaic systems. As promising efficient and long-term stable LSC fluorophores semiconductor nanocrystals like Quantum dots (QDs) with size and composition tunable optoelectronic properties have recently emerged. The most popular II/VI or IV/VI semiconductor QDs contain, however, potentially hazardous cadmium or lead ions, which is a bottleneck for commercial applications. A simple aqueous based, microwaveassisted synthesis for environmentally friendly and highly emissive AgInS2/ ZnS QDs is developed using 3-mercaptopropionic acid (MPA) and glutathione (GSH) and their incorporation into polylaurylmethacrylate (PLMA) polymer slabs integrable in LSC devices (10.4 × 10.4 × 0.2 cm3, G = 12.98).
With this simple approach, optical power efficiencies (OPE) of 3.8% and 3.6% and optical quantum efficiencies (OQE) of 24.1% and 27.4% are obtained, which are among the highest values yet reported.
We present a workflow for obtaining fully trained artificial neural networks that can perform automatic particle segmentations of agglomerated, non-spherical nanoparticles from scanning electron microscopy images “from scratch”, without the need for large training data sets of manually annotated images. The whole process only requires about 15 minutes of hands-on time by a user and can typically be finished within less than 12 hours when training on a single graphics card (GPU). After training, SEM image analysis can be carried out by the artificial neural network within seconds. This is achieved by using unsupervised learning for most of the training dataset generation, making heavy use of generative adversarial networks and especially unpaired image-to-image translation via cycle-consistent adversarial networks. We compare the segmentation masks obtained with our suggested workflow qualitatively and quantitatively to state-of-the-art methods using various metrics. Finally, we used the segmentation masks for automatically extracting particle size distributions from the SEM images of TiO2 particles, which were in excellent agreement with particle size distributions obtained manually but could be obtained in a fraction of the time.