From prediction to design: Recent advances in machine learning for the study of 2D materials

He, Hua; Wang, Yuhua; Qi, Yajuan; Xu, Zichao; Li, Yue; Wang, Yumei

doi:10.1016/j.nanoen.2023.108965

Cited by 28 publications

(15 citation statements)

References 102 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While DFT entails approximations compared to more rigorous quantum mechanics, its computational efciency enables its widespread application across various scientifc domains [145]. Its adaptability spans from unraveling biological processes to engineering innovative technologies, albeit necessitating expert guidance for appropriate approximation selection and interpretation of results [146]. Nonetheless, DFT fundamental role in elucidating electron dynamics within molecules underscores its pivotal contribution to advancing chemistry, material science, and energy storage devices.…”

Section: Te Use Of Dft In Investigating Supercapacitorsmentioning

confidence: 99%

A Review on the Recent Advances in Battery Development and Energy Storage Technologies

Njema,

Ouma,

Kibet

2024

Journal of Renewable Energy

View full text Add to dashboard Cite

Energy storage is a more sustainable choice to meet net-zero carbon foot print and decarbonization of the environment in the pursuit of an energy independent future, green energy transition, and uptake. The journey to reduced greenhouse gas emissions, increased grid stability and reliability, and improved green energy access and security are the result of innovation in energy storage systems. Renewable energy sources are fundamentally intermittent, which means they rely on the availability of natural resources like the sun and wind rather than continuously producing energy. Due to its ability to address the inherent intermittency of renewable energy sources, manage peak demand, enhance grid stability and reliability, and make it possible to integrate small-scale renewable energy systems into the grid, energy storage is essential for the continued development of renewable energy sources and the decentralization of energy generation. Accordingly, the development of an effective energy storage system has been prompted by the demand for unlimited supply of energy, primarily through harnessing of solar, chemical, and mechanical energy. Nonetheless, in order to achieve green energy transition and mitigate climate risks resulting from the use of fossil-based fuels, robust energy storage systems are necessary. Herein, the need for better, more effective energy storage devices such as batteries, supercapacitors, and bio-batteries is critically reviewed. Due to their low maintenance needs, supercapacitors are the devices of choice for energy storage in renewable energy producing facilities, most notably in harnessing wind energy. Moreover, supercapacitors possess robust charging and discharging cycles, high power density, low maintenance requirements, extended lifespan, and are environmentally friendly. On the other hand, combining aluminum with nonaqueous charge storage materials such as conductive polymers to make use of each material’s unique capabilities could be crucial for continued development of robust storage batteries. In general, energy density is a key component in battery development, and scientists are constantly developing new methods and technologies to make existing batteries more energy proficient and safe. This will make it possible to design energy storage devices that are more powerful and lighter for a range of applications. When there is an imbalance between supply and demand, energy storage systems (ESS) offer a way of increasing the effectiveness of electrical systems. They also play a central role in enhancing the reliability and excellence of electrical networks that can also be deployed in off-grid localities.

show abstract

Section: Te Use Of Dft In Investigating Supercapacitorsmentioning

confidence: 99%

A Review on the Recent Advances in Battery Development and Energy Storage Technologies

Njema,

Ouma,

Kibet

2024

Journal of Renewable Energy

View full text Add to dashboard Cite

show abstract

“…The development of sensors has required a lot of labor based on new, very sensitive, and selective materials. 25,155 Nonetheless, the following several obstacles prevent 2D materials from widely being used as the best sensing materials and sensor systems. In low light, a lot of 2D sensors function.…”

Section: Outcomes and Impact Of Ml-assisted Sensingmentioning

confidence: 99%

“…ML algorithms can optimize sensor response by dynamically adjusting the parameters. By continuously assessing sensor performance and recalibrating sensors as needed, ML algorithms can produce accurate and consistent results. , To obtain a more comprehensive understanding of their surroundings, sensors can employ ML to combine information from many sensing modalities, including environmental sensors, accelerometers, and cameras. ML algorithms can predict when sensors or equipment will malfunction based on historical data.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Assisted Enhancement in a Two-Dimensional Material’s Sensing Performance

Das,

Mazumdar,

Khondakar

et al. 2024

ACS Appl. Nano Mater.

View full text Add to dashboard Cite

materials have shown a dramatic increase in use in recent years due to their exceptional characteristics, which make them perfect for a wide range of sensing applications. However, achieving optimal sensing performance in 2D material-based sensors often poses challenges owing to material limitations and environmental factors. The combination of machine learning (ML) algorithms with 2D materials offers a way to maximize selectivity, sensitivity, and overall sensor dependability. This study starts by looking at the basic characteristics of many 2D materials and their uses in sensing, such as graphene and transition metal dichalcogenides (TMDs). It then explores the difficulties encountered by conventional sensing techniques and shows how ML techniques overcome these difficulties. A thorough examination of the various ML methods used with 2D materials is provided, along with an explanation of their functions in data processing, pattern identification, and real-time adaptive sensing. This paper also discusses how ML might lead to better performance measures including lower false positive rates and higher accuracy. Comprehensive analysis is done on case studies that demonstrate effective implementations in many sensing domains, such as industrial applications, environmental monitoring, and healthcare. In conclusion, this article discusses prospects for the future, highlighting how ML-assisted 2D materials-based sensors are developing and how they might transform sensing technologies in a variety of fields.

show abstract

“…ML can establish nonlinear relationships by fitting complex input and output functions, which are related to the properties of potential catalysts. 36 This tool is mainly applied in four aspects of materials science: 37 promoting the synthesis and exploration of materials, 38 predicting the properties of materials, 39 characterizing the microstructure of materials, 40 and accelerating the development of computational simulation. 41 ML is an effective tool for predicting catalytic activity, optimization of catalysts, identification of active sites, and design of reaction pathways in the CO 2 RR.…”

Section: Introductionmentioning

confidence: 99%

Micro-kinetic modelling of the CO reduction reaction on single atom catalysts accelerated by machine learning

Zhang,

Wang,

Zhang

et al. 2024

Phys. Chem. Chem. Phys.

View full text Add to dashboard Cite

show abstract

From prediction to design: Recent advances in machine learning for the study of 2D materials

Cited by 28 publications

References 102 publications

A Review on the Recent Advances in Battery Development and Energy Storage Technologies

A Review on the Recent Advances in Battery Development and Energy Storage Technologies

Machine Learning Assisted Enhancement in a Two-Dimensional Material’s Sensing Performance

Micro-kinetic modelling of the CO reduction reaction on single atom catalysts accelerated by machine learning

Contact Info

Product

Resources

About