Inverse design of composite metal oxide optical materials based on deep transfer learning and global optimization

Dong, Rongzhi; Dan, Yabo; Li, Xiang; Hu, Jianjun

doi:10.1016/j.commatsci.2020.110166

Cited by 28 publications

(21 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The combination of topology optimization methods and DL algorithms (such as AAEs) promotes a wider range of optimization design and data-driven material synthesis and significantly improves computational efficiency [111]. The hybrid model of DL and global optimization algorithms (Bayesian optimization and GA) can well solve the problem that DL models require a large number of data sets, and efficiently and accurately reverse the material composition [127]. Using a hybrid finite element algorithm and feedforward neural network model, it is possible to design and design high-performance structural ceramics that experience thermal load [128].…”

Section: Hybrid Models With Other Algorithmsmentioning

confidence: 99%

“…In a hybrid model composed of DNNs and migration learning algorithms, migration learning is used to solve typical small data collection problems in materials. The DNN model can predict the complete UV-vis absorption spectrum of the material from the compound formula; through the initial migration learning training and fine-tuning of parameters, the prediction model performs well in the prediction of the spectrum of metal oxide materials containing only composition information [127].…”

Section: Hybrid Models With Other Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning modeling strategy for material science: from natural materials to metamaterials

Chen

Xiong

et al. 2022

J. Phys. Mater.

View full text Add to dashboard Cite

Computational modeling is a crucial approach in material-related research for discovering new materials with superior properties. However, the high design flexibility in materials, especially in the realm of metamaterials where the sub-wavelength structure provides an additional degree of freedom in design, poses a formidable computational cost in various real-world applications. With the advent of big data, deep learning brings revolutionary breakthroughs in many conventional machine learning and pattern recognition tasks such as image classification. The accompanied data-driven modeling paradigm also provides transformative methodology shift in materials science, from trial-and-error routine to intelligent material discovery and analysis. This review systematically summarize the application of deep learning in material science, based on a model selection perspective for both natural materials and metamaterials. The review aims to uncover the logic behind data-model relation with emphasis on suitable data structures for different scenarios in the material study and the corresponding problem-solving deep learning model architectures.

show abstract

Section: Hybrid Models With Other Algorithmsmentioning

confidence: 99%

Section: Hybrid Models With Other Algorithmsmentioning

confidence: 99%

Deep learning modeling strategy for material science: from natural materials to metamaterials

Chen

Xiong

et al. 2022

J. Phys. Mater.

View full text Add to dashboard Cite

show abstract

“…Some promising predictive capabilities are emerging from the use of machine learning approaches in computational materials science and will likely drive the future discovery of proper dopants for selected noncritical MOSs in order to tune their photoconversion performance in the different discussed field. [340][341][342][343] The term "doping" referred here has not the same meaning used in the well-known silicon-based (and other crystalline semiconductors) technology in which a very low concentration of dopants (e.g., boron or phosphorus) substitute the silicon atoms in the crystal lattice with the goal of increasing the free carrier density of silicon without altering the physicochemical properties of the semiconductor (e.g., lattice, chemical stability, energy bandgap, and carriers mobility). Indeed, doping in MOSs gains a much wider meaning in which, as summarized in Table 2, the addition of dopants in the MO lattice is important not only to increase the density of charge carriers (i.e., improving the conductivity), but it is also useful for tuning other properties such as photosensitivity and thermoelectricity, and for engineering the lattice structures and its interplay with others materials, therefore introducing additional degree of freedom in designing novel energy conversion and storage devices.…”

Section: Conclusion and Future Perspectivesmentioning

confidence: 99%

Opportunities from Doping of Non‐Critical Metal Oxides in Last Generation Light‐Conversion Devices

Gatti

Lamberti

Mazzaro

et al. 2021

Advanced Energy Materials

View full text Add to dashboard Cite

The need to develop sustainable energy solutions is an urgent requirement for society, with the additional requirement to limit dependence on critical raw materials, within a virtuous circular economy model. In this framework, it is essential to identify new avenues for light‐conversion into clean energy and fuels exploiting largely available materials and green production methods. Metal oxide semiconductors (MOSs) emerge among other species for their remarkable environmental stability, chemical tunability, and optoelectronic properties. MOSs are often key constituents in next generation energy devices, mainly in the role of charge selective layers. Their use as light harvesters is hitherto rather limited, but progressively emerging. One of the key strategies to boost their properties involves doping, that can improve charge mobility, light absorption and tune band structures to maximize charge separation at heterojunctions. In this review, effective methods to dope MOSs and to exploit the derived benefits in relation to performance enhancement in different types of devices are identified and critically compared. The work is focused specifically on the best opportunities coming from the use of non‐critical raw materials, so as to contribute in defining an economically feasible roadmap for light conversion technologies based on these highly stable and widely available compounds.

show abstract

“…Bayesian optimization (BO) is an iterative sequential learning 1 algorithm that simultaneously improves model accuracy through exploration of high-uncertainty regions and exploitation of highperforming parameter combinations. It is bestsuited for expensive-to-evaluate models with a limited budget of design iterations, and has seen increasing usage in materials informatics [1][2][3][4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

High-dimensional Bayesian Optimization of Hyperparameters for an Attention-based Network to Predict Materials Property: a Case Study on CrabNet using Ax and SAASBO

Baird¹,

Liu²,

Sparks³

2022

Preprint

View full text Add to dashboard Cite

Expensive-to-train deep learning models can benefit from an optimization of the hyperparameters that determine the model architecture. We optimize 23 hyperparameters of a materials informatics model, Compositionally-Restricted Attention-Based Network (CrabNet), over 100 adaptive design iterations using two models within the Adaptive Experimentation (Ax) Platform. This includes a recently developed Bayesian optimization (BO) algorithm, sparse axis-aligned subspaces Bayesian optimization (SAASBO), which has shown exciting performance on high-dimensional optimization tasks. Using SAASBO to optimize CrabNet hyperparameters, we demonstrate a new state-of-the-art on the experimental band gap regression task within the materials informatics benchmarking platform, Matbench (∼4.5 % decrease in mean absolute error (MAE) relative to incumbent). Characteristics of the adaptive design scheme as well as feature importances are described for each of the Ax models. SAASBO has great potential to both improve existing surrogate models, as shown in this work, and in future work, to efficiently discover new, high-performing materials in high-dimensional materials science search spaces.

show abstract

Inverse design of composite metal oxide optical materials based on deep transfer learning and global optimization

Cited by 28 publications

References 52 publications

Deep learning modeling strategy for material science: from natural materials to metamaterials

Deep learning modeling strategy for material science: from natural materials to metamaterials

Opportunities from Doping of Non‐Critical Metal Oxides in Last Generation Light‐Conversion Devices

High-dimensional Bayesian Optimization of Hyperparameters for an Attention-based Network to Predict Materials Property: a Case Study on CrabNet using Ax and SAASBO

Contact Info

Product

Resources

About