Dataset Information

Machine learning of atomic force microscopy images of organic solar cells.

ABSTRACT: The bulk heterojunction structures of organic photovoltaics (OPVs) have been overlooked in their machine learning (ML) approach despite their presumably significant impact on power conversion efficiency (PCE). In this study, we examined the use of atomic force microscopy (AFM) images to construct an ML model for predicting the PCE of polymer : non-fullerene molecular acceptor OPVs. We manually collected experimentally observed AFM images from the literature, applied data curing and performed image analyses (fast Fourier transform, FFT; gray-level co-occurrence matrix, GLCM; histogram analysis, HA) and ML linear regression. The accuracy of the model did not considerably improve even by including AFM data in addition to the chemical structure fingerprints, material properties and process parameters. However, we found that a specific spatial wavelength of FFT (40-65 nm) significantly affects PCE. The GLCM and HA methods, such as homogeneity, correlation and skewness expand the scope of image analysis and artificial intelligence in materials science research fields.

SUBMITTER: Kobayashi Y

PROVIDER: S-EPMC10189247 | biostudies-literature | 2023 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning of atomic force microscopy images of organic solar cells.

Kobayashi Yasuhito Y Miyake Yuta Y Ishiwari Fumitaka F Ishiwata Shintaro S Saeki Akinori A

RSC advances 20230516 22

The bulk heterojunction structures of organic photovoltaics (OPVs) have been overlooked in their machine learning (ML) approach despite their presumably significant impact on power conversion efficiency (PCE). In this study, we examined the use of atomic force microscopy (AFM) images to construct an ML model for predicting the PCE of polymer : non-fullerene molecular acceptor OPVs. We manually collected experimentally observed AFM images from the literature, applied data curing and performed ima ...[more]

PMID: 37207099

Similar Datasets

Project description:In the course of the development of the nervous system, neuronal cells extend (grow) axons, which navigate over distances of the order of many cell diameters to reach target dendrites from other neurons and establish neuronal circuits. Some of the central challenges in biophysics today are to develop a quantitative model of axonal growth, which includes the interactions between the neurons and their growth environment, and to describe the complex architecture of neuronal networks in terms of a small number of physical variables. To address these challenges, researchers need new experimental techniques for measuring biomechanical interactions with very high force and spatiotemporal resolutions. Here we report a unique experimental approach that integrates three different high-resolution techniques on the same platform-traction force microscopy (TFM), atomic force microscopy (AFM) and fluorescence microscopy (FM)-to measure biomechanical properties of cortical neurons. To our knowledge, this is the first literature report of combined TFM/AFM/FM measurements performed for any type of cell. Using this combination of powerful experimental techniques, we perform high-resolution measurements of the elastic modulus for cortical neurons and relate these values with traction forces exerted by the cells on the growth substrate (poly acrylamide hydrogels, or PAA, coated with poly D-lysine). We obtain values for the traction stresses exerted by the cortical neurons in the range 30-70 Pa, and traction forces in the range 5-11 nN. Our results demonstrate that neuronal cells stiffen when axons exert forces on the PAA substrate, and that neuronal growth is governed by a contact guidance mechanism, in which axons are guided by external mechanical cues. This work provides new insights for bioengineering novel biomimetic platforms that closely model neuronal growth in vivo, and it has significant impact for creating neuroprosthetic interfaces and devices for neuronal growth and regeneration.

Dataset Information

Machine learning of atomic force microscopy images of organic solar cells.

Publications

Machine learning of atomic force microscopy images of organic solar cells.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets