Nanomaterials Discovery and Design through Machine Learning

Wang, Ming; Wang, Ting; Cai, Pingqiang; Chen, Xiaodong

doi:10.1002/smtd.201900025

Cited by 84 publications

(54 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As early as 1993, the use of machine learning to study the solubility of C 60 was proposed . Machine learning has been widely used to predict the toxicity of nanomaterials, to discover new nontoxic nanoparticles, to develop multistructure/single‐property relationships of nanoparticles, to study quantum‐mechanical observables of molecular systems, to analyze chemical reactions of nanomaterials and to solve kinetic systems . Oh et al successfully applied meta‐analysis to study the chemical toxicity of quantum dots (QDs).…”

Section: Applicationsmentioning

confidence: 99%

“…The scientific literature and experimental records contain a large amount of material data to which machine learning can be applied, such as molecular properties, reaction conditions, and synthetic formulations. Using text mining, these useful data, which are scattered among articles, journals and magazines, can be quickly collected, which will substantially enrich the existing material databases and enable the creation of specialized databases …”

Section: Prospectsmentioning

confidence: 99%

“…With artificial intelligence and machine learning coming of age, important advances are being made not only by researchers in the mainstream artificial intelligence field but also by experts in other fields who are employing these methods to realize their own objectives. Early in the last century, machine learning was used to detect the solubility of C 60 in materials science, and it has now been used to discover new materials, to predict material and molecular properties, to study quantum chemistry, and to design drugs . As the resources and tools for machine learning are abundant and easy to access, the barrier to entry for applying machine learning in materials science is lower than ever.…”

Section: Introductionmentioning

confidence: 99%

“…Early in the last century, machine learning was used to detect the solubility of C 60 in materials science, 12 and it has now been used to discover new materials, to predict material and molecular properties, to study quantum chemistry, and to design drugs. [13][14][15][16][17] As the resources and tools for machine learning are abundant and easy to access, the barrier to entry for applying machine learning in materials science is lower than ever.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Machine learning in materials science

Wei

Chu

Sun

et al. 2019

InfoMat

631

298

View full text Add to dashboard Cite

Traditional methods of discovering new materials, such as the empirical trial and error method and the density functional theory (DFT)‐based method, are unable to keep pace with the development of materials science today due to their long development cycles, low efficiency, and high costs. Accordingly, due to its low computational cost and short development cycle, machine learning is coupled with powerful data processing and high prediction performance and is being widely used in material detection, material analysis, and material design. In this article, we discuss the basic operational procedures in analyzing material properties via machine learning, summarize recent applications of machine learning algorithms to several mature fields in materials science, and discuss the improvements that are required for wide‐ranging application.

show abstract

Section: Applicationsmentioning

confidence: 99%

Section: Prospectsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Machine learning in materials science

Wei

Chu

Sun

et al. 2019

InfoMat

631

298

View full text Add to dashboard Cite

show abstract

“…Deep learning uses multiple levels of nonlinear functions to learn high‐level representation of input data layer‐by‐layer for making decision. The learned representation is often abstract and composite, which can serve as input for the latter layers . Therefore, deep learning technologies possess the ability of automated feature learning and provide an end‐to‐end learning paradigm to obtain the desired knowledge from complex sensor data.…”

Section: Machine Learning and Edging Computingmentioning

confidence: 99%

Cyber–Physiochemical Interfaces

et al. 2020

Self Cite

View full text Add to dashboard Cite

Living things rely on various physical, chemical, and biological interfaces, e.g., somatosensation, olfactory/gustatory perception, and nervous system response. They help organisms to perceive the world, adapt to their surroundings, and maintain internal and external balance. Interfacial information exchanges are complicated but efficient, delicate but precise, and multimodal but unisonous, which has driven researchers to study the science of such interfaces and develop techniques with potential applications in health monitoring, smart robotics, future wearable devices, and cyber physical/human systems. To understand better the issues in these interfaces, a cyber–physiochemical interface (CPI) that is capable of extracting biophysical and biochemical signals, and closely relating them to electronic, communication, and computing technology, to provide the core for aforementioned applications, is proposed. The scientific and technical progress in CPI is summarized, and the challenges to and strategies for building stable interfaces, including materials, sensor development, system integration, and data processing techniques are discussed. It is hoped that this will result in an unprecedented multi‐disciplinary network of scientific collaboration in CPI to explore much uncharted territory for progress, providing technical inspiration—to the development of the next‐generation personal healthcare technology, smart sports‐technology, adaptive prosthetics and augmentation of human capability, etc.

show abstract

Mechanically Interlocked Hydrogel–Elastomer Hybrids for On‐Skin Electronics

Pan

Zhang

Cai

et al. 2020

Adv Funct Materials

Self Cite

141

105

View full text Add to dashboard Cite

Soft electronics that seamlessly interface with skin are of great interest in health monitoring and human-machine interfaces. However, achieving mechanical softness, skin adhesiveness, and high conductivity concurrently has always been a major challenge due to the difficulty in bonding dissimilar materials while retaining their respective properties. Herein, the mechanically interlocked hydrogel-elastomer hybrid is reported as a viable solution to this problem. Hydrogels with low moduli and high adhesiveness were employed as the substrate, while porous elastomer webs were used as matrices to load conductive films and lock the hydrogels through a mechanically interlocked structure. The bonding strength between hydrogel and elastomer in the interlocking hybrid structure was 14.3 times of that of physical stacking method. As a proof of concept, interlocking hybrids were used as on-skin electrodes for electrophysiological signals recording including electromyography and electrocardiogram.The robust hybrid electrodes still well detect signals after multiple cycles. The proposed

show abstract

Nanomaterials Discovery and Design through Machine Learning

Cited by 84 publications

References 66 publications

Machine learning in materials science

Machine learning in materials science

Cyber–Physiochemical Interfaces

Mechanically Interlocked Hydrogel–Elastomer Hybrids for On‐Skin Electronics

Contact Info

Product

Resources

About