Machine learning-assisted development of organic photovoltaics via high-throughput in-situ formulation

2021 ◽  
Author(s):  
Na Gyeong An ◽  
Doojin Vak ◽  
Jin Young Kim
Keyword(s):  
Machine Learning ◽  
High Throughput ◽  
Organic Photovoltaics ◽  
High Performance ◽  
Manufacturing Technology ◽  
Ternary Blend

Discovery of high-performance non-fullerene acceptors and ternary blend systems have resulted in a breakthrough in the efficiency of organic photovoltaics (OPVs) and created new opportunities for commercialization. However, manufacturing technology...

scholarly journals Lead candidates for high-performance organic photovoltaics from high-throughput quantum chemistry – the Harvard Clean Energy Project

2014 ◽  
Vol 7 (2) ◽  
pp. 698-704 ◽  
Author(s):  
Johannes Hachmann ◽  
Roberto Olivares-Amaya ◽  
Adrian Jinich ◽  
Anthony L. Appleton ◽  
Martin A. Blood-Forsythe ◽  
...  
Keyword(s):  
Quantum Chemistry ◽  
High Throughput ◽  
Organic Photovoltaics ◽  
High Performance ◽  
Clean Energy

Machine-learning-assisted high-throughput computational screening of high performance metal–organic frameworks

2020 ◽  
Vol 5 (4) ◽  
pp. 725-742 ◽  
Author(s):  
Zenan Shi ◽  
Wenyuan Yang ◽  
Xiaomei Deng ◽  
Chengzhi Cai ◽  
Yaling Yan ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Throughput ◽  
High Performance ◽  
Metal Organic Frameworks ◽  
Computational Screening ◽  
Metal Organic

The combination of machine learning and high-throughput computation for the screening of MOFs with high performance.

In Situ Electrochemical Deposition and Doping of C60Films Applied to High-Performance Inverted Organic Photovoltaics

2012 ◽  
Vol 24 (42) ◽  
pp. 5727-5731 ◽  
Author(s):  
Cheng Gu ◽  
Zhongbo Zhang ◽  
Shuheng Sun ◽  
Yuyu Pan ◽  
Chengmei Zhong ◽  
...  
Keyword(s):  
Electrochemical Deposition ◽  
Organic Photovoltaics ◽  
High Performance

scholarly journals A survey of algorithms for transforming molecular dynamics data into metadata for in situ analytics based on machine learning methods

2020 ◽  
Vol 378 (2166) ◽  
pp. 20190063
Author(s):  
Michela Taufer ◽  
Trilce Estrada ◽  
Travis Johnston
Keyword(s):  
Machine Learning ◽  
Molecular Dynamics ◽  
Drug Design ◽  
High Performance ◽  
Molecular System ◽  
Md Simulations ◽  
Ligand Docking ◽  
Learning Methods ◽  
Machine Learning Methods

This paper presents the survey of three algorithms to transform atomic-level molecular snapshots from molecular dynamics (MD) simulations into metadata representations that are suitable for in situ analytics based on machine learning methods. MD simulations studying the classical time evolution of a molecular system at atomic resolution are widely recognized in the fields of chemistry, material sciences, molecular biology and drug design; these simulations are one of the most common simulations on supercomputers. Next-generation supercomputers will have a dramatically higher performance than current systems, generating more data that needs to be analysed (e.g. in terms of number and length of MD trajectories). In the future, the coordination of data generation and analysis can no longer rely on manual, centralized analysis traditionally performed after the simulation is completed or on current data representations that have been defined for traditional visualization tools. Powerful data preparation phases (i.e. phases in which original row data is transformed to concise and still meaningful representations) will need to proceed data analysis phases. Here, we discuss three algorithms for transforming traditionally used molecular representations into concise and meaningful metadata representations. The transformations can be performed locally. The new metadata can be fed into machine learning methods for runtime in situ analysis of larger MD trajectories supported by high-performance computing. In this paper, we provide an overview of the three algorithms and their use for three different applications: protein–ligand docking in drug design; protein folding simulations; and protein engineering based on analytics of protein functions depending on proteins' three-dimensional structures. This article is part of a discussion meeting issue ‘Numerical algorithms for high-performance computational science’.

scholarly journals Predictive Power of Machine Learning for Optimizing Solar Water Heater Performance: The Potential Application of High-Throughput Screening

2017 ◽  
Vol 2017 ◽  
pp. 1-10 ◽  
Author(s):  
Hao Li ◽  
Zhijian Liu ◽  
Kejun Liu ◽  
Zhien Zhang
Keyword(s):  
Machine Learning ◽  
High Throughput ◽  
Potential Application ◽  
High Throughput Screening ◽  
High Performance ◽  
Predictive Power ◽  
Prediction Method ◽  
Solar Water Heater ◽  
Water Heater ◽  
Solar Water

Predicting the performance of solar water heater (SWH) is challenging due to the complexity of the system. Fortunately, knowledge-based machine learning can provide a fast and precise prediction method for SWH performance. With the predictive power of machine learning models, we can further solve a more challenging question: how to cost-effectively design a high-performance SWH? Here, we summarize our recent studies and propose a general framework of SWH design using a machine learning-based high-throughput screening (HTS) method. Design of water-in-glass evacuated tube solar water heater (WGET-SWH) is selected as a case study to show the potential application of machine learning-based HTS to the design and optimization of solar energy systems.

scholarly journals High-performance ternary blend all-polymer solar cells with complementary absorption bands from visible to near-infrared wavelengths

2016 ◽  
Vol 9 (1) ◽  
pp. 135-140 ◽  
Author(s):  
Hiroaki Benten ◽  
Takaya Nishida ◽  
Daisuke Mori ◽  
Huajun Xu ◽  
Hideo Ohkita ◽  
...  
Keyword(s):  
Thin Film ◽  
Solar Cells ◽  
Organic Photovoltaics ◽  
High Performance ◽  
Near Infrared ◽  
Polymer Solar Cells ◽  
Ternary Blend ◽  
Absorption Bands ◽  
Infrared Wavelengths

Ternary blend all-polymer solar cells open a new avenue for accelerating improvement in the efficiency of non-fullerene thin-film organic photovoltaics.

High-throughput image segmentation and machine learning approaches in the plant sciences across multiple scales

2021 ◽  
Author(s):  
Eli Buckner ◽  
Haonan Tong ◽  
Chanae Ottley ◽  
Cranos Williams
Keyword(s):  
Machine Learning ◽  
Image Segmentation ◽  
High Throughput ◽  
Stress Responses ◽  
High Performance ◽  
Multiple Scales ◽  
Cell Communication ◽  
Plant Diseases ◽  
Learning Approaches ◽  
Plant Image

Agriculture has benefited greatly from the rise of big data and high-performance computing. The acquisition and analysis of data across biological scales have resulted in strategies modeling inter- actions between plant genotype and environment, models of root architecture that provide insight into resource utilization, and the elucidation of cell-to-cell communication mechanisms that are instrumental in plant development. Image segmentation and machine learning approaches for interpreting plant image data are among many of the computational methodologies that have evolved to address challenging agricultural and biological problems. These approaches have led to contributions such as the accelerated identification of gene that modulate stress responses in plants and automated high-throughput phenotyping for early detection of plant diseases. The continued acquisition of high throughput imaging across multiple biological scales provides opportunities to further push the boundaries of our understandings quicker than ever before. In this review, we explore the current state of the art methodologies in plant image segmentation and machine learning at the agricultural, organ, and cellular scales in plants. We show how the methodologies for segmentation and classification differ due to the diversity of physical characteristics found at these different scales. We also discuss the hardware technologies most commonly used at these different scales, the types of quantitative metrics that can be extracted from these images, and how the biological mechanisms by which plants respond to abiotic/biotic stresses or genotypic modifications can be extracted from these approaches.

High performance Nanogold™-in situ hybridzation and its use in the detection of hybridized and PCR-amplified microscopical preparations

1996 ◽  
Vol 54 ◽  
pp. 896-897
Author(s):  
G. W. Hacker ◽  
I. Zehbe ◽  
J. Hainfeld ◽  
A.-H. Graf ◽  
C. Hauser-Kronberger ◽  
...  
Keyword(s):  
Polymerase Chain Reaction ◽  
Messenger Rna ◽  
High Performance ◽  
Detection System ◽  
Direct Methods ◽  
Genetic Alterations ◽  
Chain Reaction ◽  
Protein Encoding ◽  
Polymerase Chain

In situ hybridization (ISH) with biotin-labeled probes is increasingly used in histology, histopathology and molecular biology, to detect genetic nucleic acid sequences of interest, such as viruses, genetic alterations and peptide-/protein-encoding messenger RNA (mRNA). In situ polymerase chain reaction (PCR) (PCR in situ hybridization = PISH) and the new in situ self-sustained sequence replication-based amplification (3SR) method even allow the detection of single copies of DNA or RNA in cytological and histological material. However, there is a number of considerable problems with the in situ PCR methods available today: False positives due to mis-priming of DNA breakdown products contained in several types of cells causing non-specific incorporation of label in direct methods, and re-diffusion artefacts of amplicons into previously negative cells have been observed. To avoid these problems, super-sensitive ISH procedures can be used, and it is well known that the sensitivity and outcome of these methods partially depend on the detection system used.

Sign in / Sign up

Export Citation Format

Share Document