Detection of topological materials with machine learning

Claussen, N.; Bernevig, B. Andrei; Regnault, Nicolas

doi:10.1103/physrevb.101.245117

Cited by 41 publications

(25 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth noting that while generation of a suitable data set-and, to a lesser extent, network training (taking ∼3 min for fixed hyper-parameters on an Nvidia 1080 Ti GPU)-requires substantial computing resources, once trained, a neural network can predict band structures orders of magnitude faster than conventional theory-driven simulations (network evaluation of a single input takes ≈ 0.02 s on an Nvidia 1080 Ti GPU). While these gains are not sufficiently attractive to merit the training of regression networks for one-or few-off calculations, they can be relevant in inverse-design problems [26,27] or highthroughput searches [53], where a very large number of distinct system configurations must be considered.…”

Section: Band Predictionmentioning

confidence: 99%

“…To do so, we extracted the 585 unit cells with Δω 12 /ω 12 ≥ 5% from the data set for use as training data. We tested three different GAN-variants [58]: a conventional GAN [53], a least squares GAN (LSGAN) [59], and Deep Regret Analytic GAN (DRAGAN) [60], each distinguished essentially by their respective generator and discriminator cost functions [61]. In each case, we adapted standard off-the-shelf implementations [62] to take a single-channel, 64 × 64 pixelized ε(r) profile as training data.…”

Section: Generative Adversarial Networkmentioning

confidence: 99%

See 1 more Smart Citation

Predictive and generative machine learning models for photonic crystals

et al. 2020

View full text Add to dashboard Cite

The prediction and design of photonic features have traditionally been guided by theory-driven computational methods, spanning a wide range of direct solvers and optimization techniques. Motivated by enormous advances in the field of machine learning, there has recently been a growing interest in developing complementary data-driven methods for photonics. Here, we demonstrate several predictive and generative data-driven approaches for the characterization and inverse design of photonic crystals. Concretely, we built a data set of 20,000 two-dimensional photonic crystal unit cells and their associated band structures, enabling the training of supervised learning models. Using these data set, we demonstrate a high-accuracy convolutional neural network for band structure prediction, with orders-of-magnitude speedup compared to conventional theory-driven solvers. Separately, we demonstrate an approach to high-throughput inverse design of photonic crystals via generative adversarial networks, with the design goal of substantial transverse-magnetic band gaps. Our work highlights photonic crystals as a natural application domain and test bed for the development of data-driven tools in photonics and the natural sciences.

show abstract

Section: Band Predictionmentioning

confidence: 99%

Section: Generative Adversarial Networkmentioning

confidence: 99%

Predictive and generative machine learning models for photonic crystals

et al. 2020

View full text Add to dashboard Cite

show abstract

“…5E ) may appear and where the magnetization direction can tune the band topology ( 45 ). These filters greatly simplify the screening, but recent work suggests that more than 30% of nonmagnetic ( 3 , 46 ) and magnetic ( 10 ) materials exhibit nontrivial topology, so there are almost certainly many more MTQMs to uncover in the TMO dataset than we have considered here.…”

Section: Resultsmentioning

confidence: 99%

High-throughput search for magnetic and topological order in transition metal oxides

et al. 2020

View full text Add to dashboard Cite

The discovery of intrinsic magnetic topological order in MnBi2Te4 has invigorated the search for materials with coexisting magnetic and topological phases. These multiorder quantum materials are expected to exhibit new topological phases that can be tuned with magnetic fields, but the search for such materials is stymied by difficulties in predicting magnetic structure and stability. Here, we compute more than 27,000 unique magnetic orderings for more than 3000 transition metal oxides in the Materials Project database to determine their magnetic ground states and estimate their effective exchange parameters and critical temperatures. We perform a high-throughput band topology analysis of centrosymmetric magnetic materials, calculate topological invariants, and identify 18 new candidate ferromagnetic topological semimetals, axion insulators, and antiferromagnetic topological insulators. To accelerate future efforts, machine learning classifiers are trained to predict both magnetic ground states and magnetic topological order without requiring first-principles calculations.

show abstract

“…2). A very recent work constructed a gradient boosting model (a particular type of powerful supervised learning algorithm) that can predict the topology of a given known material based only on "coarse-grained" chemical composition and crystal symmetry predictors with an accuracy of 90% 74 . Similar to superconductivity, such models can be used to accelerate the search for novel materials by providing fast and efficient means to predict the possible topological nature of a given candidate.…”

Section: Ai For Computational Quantum Materialsmentioning

confidence: 99%

Artificial intelligence for search and discovery of quantum materials

et al. 2021

View full text Add to dashboard Cite

Artificial intelligence and machine learning are becoming indispensable tools in many areas of physics, including astrophysics, particle physics, and climate science. In the arena of quantum materials, the rise of new experimental and computational techniques has increased the volume and the speed with which data are collected, and artificial intelligence is poised to impact the exploration of new materials such as superconductors, spin liquids, and topological insulators. This review outlines how the use of data-driven approaches is changing the landscape of quantum materials research. From rapid construction and analysis of computational and experimental databases to implementing physical models as pathfinding guidelines for autonomous experiments, we show that artificial intelligence is already well on its way to becoming the lynchpin in the search and discovery of quantum materials.

show abstract

Detection of topological materials with machine learning

Cited by 41 publications

References 38 publications

Predictive and generative machine learning models for photonic crystals

Predictive and generative machine learning models for photonic crystals

High-throughput search for magnetic and topological order in transition metal oxides

Artificial intelligence for search and discovery of quantum materials

Contact Info

Product

Resources

About