Multi-fidelity machine learning models for structure–property mapping of organic electronics

Yang, Chih-Hsuan; Pokuri, Balaji Sesha Sarath; Lee, Xian Yeow; Balakrishnan, S.; Hegde, Chinmay; Sarkar, Soumik; Ganapathysubramanian, Baskar

doi:10.1016/j.commatsci.2022.111599

Cited by 6 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Whilst machine learning has shown strong potential as an emerging paradigm for rapidly generating predictions of materials' properties of interest, as a data-driven technology its utility can be limited by the availability of high-quality data. An emerging approach to deal with this challenge is to build machine learning models built from multiple different fidelities of data, which can then act as predictors for cases where sufficient amounts of data are not available to build traditional QSAR or machine-learning models 16,17 . These approaches typically rely on building a model which is able to relate the different fidelities of information to each other, typically by building a single model with multiple output valuesone per fidelity.…”

Section: Multi-fidelity Machine Learningmentioning

confidence: 99%

A multi-fidelity machine learning approach to high throughput materials screening

et al. 2022

View full text Add to dashboard Cite

The ever-increasing capability of computational methods has resulted in their general acceptance as a key part of the materials design process. Traditionally this has been achieved using a so-called computational funnel, where increasingly accurate - and expensive – methodologies are used to winnow down a large initial library to a size which can be tackled by experiment. In this paper we present an alternative approach, using a multi-output Gaussian process to fuse the information gained from both experimental and computational methods into a single, dynamically evolving design. Common challenges with computational funnels, such as mis-ordering methods, and the inclusion of non-informative steps are avoided by learning the relationships between methods on the fly. We show this approach reduces overall optimisation cost on average by around a factor of three compared to other commonly used approaches, through evaluation on three challenging materials design problems.

show abstract

Section: Multi-fidelity Machine Learningmentioning

confidence: 99%

A multi-fidelity machine learning approach to high throughput materials screening

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In addition, the shortage of high-quality data has always been a key problem in machine learning. Multi-fidelity classification algorithms [17][18][19] solve this type of problem by incorporating information from other sources that can be obtained at a low cost while maintaining good correlation. In this regard, it can also be applied to the XSS attack detection model in the future to improve the generalization ability of the model.…”

Section: Related Workmentioning

confidence: 99%

Resolving Cross-Site Scripting Attacks through Fusion Verification and Machine Learning

Wei

Qin

et al. 2022

Mathematics

View full text Add to dashboard Cite

The frequent variations of XSS (cross-site scripting) payloads make static and dynamic analysis difficult to detect effectively. In this paper, we proposed a fusion verification method that combines traffic detection with XSS payload detection, using machine learning to detect XSS attacks. In addition, we also proposed seven new payload features to improve detection efficiency. In order to verify the effectiveness of our method, we simulated and tested 20 public CVE (Common Vulnerabilities and Exposures) XSS attacks. The experimental results show that our proposed method has better accuracy than the single traffic detection model. Among them, the recall rate increased by an average of 48%, the F1 score increased by an average of 27.94%, the accuracy rate increased by 9.29%, and the accuracy rate increased by 3.81%. Moreover, the seven new features proposed in this paper account for 34.12% of the total contribution rate of the classifier.

show abstract

Rapid Prototyping for Accelerated Establishment of Film Processing‐Performance Relationships in Silicon Phthalocyanine OFETs

Cranston,

Mauthe,

Wang

et al. 2024

Adv Elect Materials

View full text Add to dashboard Cite

Understanding the complex relationships underlying the performance of organic electronic devices, such as organic field‐effect transistors (OFETs), requires researchers to navigate a multi‐dimensional parameter space that includes material design, solution formulation, fabrication parameters, and device geometry. Herein, a recently developed materials acceleration platform is demonstrated, named the RoboMapper, to perform direct on‐chip fabrication of OFETs by ultrasonic meniscus printing using silicon phthalocyanine (SiPc) derivatives as the semiconductor. OFETs using bis(tri‐n‐butylsilyl oxide) SiPc ((3BS)2‐SiPc) exhibited the best device performance characterized by the highest electron field‐effect mobility (µe). Through optical microscopy and grazing‐incidence wide‐angle X‐ray scattering (GIWAXS), the favorable performance of (3BS)2‐SiPc is attributed to the specific film morphology and molecular packing achieved with optimal print conditions. Investigating the impact of deposition parameters reveals the crucial role of solvent evaporation rate and print speed in achieving high‐quality film formation. Overall, optimal fabrication conditions for (3BS)2‐SiPc devices include slow print speeds and fast evaporating solutions achieved by using a mixture of co‐solvents and an elevated substrate temperature. The results of this work reveal distinct relationships between deposition conditions, film properties, and device performance for each SiPc derivative and emphasize the necessity of high throughput experimentation to comprehensively understand process‐performance relationships in organic semiconductors.

show abstract

Multi-fidelity machine learning models for structure–property mapping of organic electronics

Cited by 6 publications

References 26 publications

A multi-fidelity machine learning approach to high throughput materials screening

A multi-fidelity machine learning approach to high throughput materials screening

Resolving Cross-Site Scripting Attacks through Fusion Verification and Machine Learning

Rapid Prototyping for Accelerated Establishment of Film Processing‐Performance Relationships in Silicon Phthalocyanine OFETs

Contact Info

Product

Resources

About