S2SNet: A Pretrained Neural Network for Superconductivity Discovery

• URL: http://arxiv.org/abs/2306.16270v1
• Date: Wed, 28 Jun 2023 14:52:50 GMT
• Title: S2SNet: A Pretrained Neural Network for Superconductivity Discovery
• Authors: Ke Liu and Kaifan Yang and Jiahong Zhang and Renjun Xu
• Abstract summary: We propose a novel model, S2SNet, which utilizes the attention mechanism for superconductivity prediction. S2SNet makes a new state-of-the-art, with out-of-sample accuracy of 92% and Area Under Curve (AUC) of 0.92.
• Score: 4.114842429117009
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Superconductivity allows electrical current to flow without any energy loss, and thus making solids superconducting is a grand goal of physics, material science, and electrical engineering. More than 16 Nobel Laureates have been awarded for their contribution to superconductivity research. Superconductors are valuable for sustainable development goals (SDGs), such as climate change mitigation, affordable and clean energy, industry, innovation and infrastructure, and so on. However, a unified physics theory explaining all superconductivity mechanism is still unknown. It is believed that superconductivity is microscopically due to not only molecular compositions but also the geometric crystal structure. Hence a new dataset, S2S, containing both crystal structures and superconducting critical temperature, is built upon SuperCon and Material Project. Based on this new dataset, we propose a novel model, S2SNet, which utilizes the attention mechanism for superconductivity prediction. To overcome the shortage of data, S2SNet is pre-trained on the whole Material Project dataset with Masked-Language Modeling (MLM). S2SNet makes a new state-of-the-art, with out-of-sample accuracy of 92% and Area Under Curve (AUC) of 0.92. To the best of our knowledge, S2SNet is the first work to predict superconductivity with only information of crystal structures. This work is beneficial to superconductivity discovery and further SDGs. Code and datasets are available in https://github.com/zjuKeLiu/S2SNet

Related papers

• Deep Learning Based Superconductivity: Prediction and Experimental Tests [2.78539995173967]
  We develop an approach based on deep learning (DL) to predict new superconducting materials. We have synthesized a compound derived from our DL network and confirmed its superconducting properties. In particular, RFs require knowledge of the chem-ical properties of the compound, while our neural net inputs depend solely on the chemical composition.
  arXiv  Detail & Related papers  (2024-12-17T15:33:48Z)
• Electron-Electron Interactions in Device Simulation via Non-equilibrium Green's Functions and the GW Approximation [71.63026504030766]
  electron-electron (e-e) interactions must be explicitly incorporated in quantum transport simulation. This study is the first one reporting large-scale atomistic quantum transport simulations of nano-devices under non-equilibrium conditions.
  arXiv  Detail & Related papers  (2024-12-17T15:05:33Z)
• Quantum thermodynamics with a single superconducting vortex [44.99833362998488]
  We demonstrate complete control over dynamics of a single superconducting vortex in a nanostructure. Our device allows us to trap the vortex in a field-cooled aluminum nanosquare and expel it on demand with a nanosecond pulse of electrical current.
  arXiv  Detail & Related papers  (2024-02-09T14:16:20Z)
• Prediction of superconducting properties of materials based on machine learning models [3.7492020569920723]
  This manuscript proposes the use of XGBoost model to identify superconductors. The first application of deep forest model to predict the critical temperature of superconductors. The first application of deep forest to predict the band gap of materials. The first sub-network model to predict the Fermi energy level of materials.
  arXiv  Detail & Related papers  (2022-11-06T10:24:21Z)
• Silicide-based Josephson field effect transistors for superconducting qubits [0.0]
  An alternative "gatemon" qubit has recently appeared, which uses hybrid superconducting/semiconducting (S/Sm) devices as gate-tuned Josephson junctions. A scalable gatemon design could be made with CMOS Josephson Field-Effect Transistors as tunable weak link. A successful gate modulation of Andreev current in a silicon-based transistor represents a step towards fully CMOS-integrated superconducting quantum computers.
  arXiv  Detail & Related papers  (2022-09-06T18:00:03Z)
• First design of a superconducting qubit for the QUB-IT experiment [50.591267188664666]
  The goal of the QUB-IT project is to realize an itinerant single-photon counter exploiting Quantum Non Demolition (QND) measurements and entangled qubits. We present the design and simulation of the first superconducting device consisting of a transmon qubit coupled to a resonator using Qiskit-Metal.
  arXiv  Detail & Related papers  (2022-07-18T07:05:10Z)
• Slowing down light in a qubit metamaterial [98.00295925462214]
  superconducting circuits in the microwave domain still lack such devices. We demonstrate slowing down electromagnetic waves in a superconducting metamaterial composed of eight qubits coupled to a common waveguide. Our findings demonstrate high flexibility of superconducting circuits to realize custom band structures.
  arXiv  Detail & Related papers  (2022-02-14T20:55:10Z)
• Observation of Superconductivity Induced Ferromagnetism in an Fe-Chalcogenide Superconductor [0.44940580193534013]
  We report nanoscale quantum sensing and imaging of magnetic flux generated by exfoliated FeTexSe1-x flakes. The coexistence of superconductivity and ferromagnetism in an established topological superconductor opens up new opportunities for exploring exotic spin and charge transport phenomena in quantum materials.
  arXiv  Detail & Related papers  (2021-06-30T08:15:58Z)
• Quantum Sensors for Microscopic Tunneling Systems [58.720142291102135]
  tunneling Two-Level-Systems (TLS) are important for micro-fabricated quantum devices such as superconducting qubits. We present a method to characterize individual TLS in virtually arbitrary materials deposited as thin-films. Our approach opens avenues for quantum material spectroscopy to investigate the structure of tunneling defects.
  arXiv  Detail & Related papers  (2020-11-29T09:57:50Z)
• Coherent superconducting qubits from a subtractive junction fabrication process [48.7576911714538]
  Josephson tunnel junctions are the centerpiece of almost any superconducting electronic circuit, including qubits. In recent years, sub-micron scale overlap junctions have started to attract attention. This work paves the way towards a more standardized process flow with advanced materials and growth processes, and constitutes an important step for large scale fabrication of superconducting quantum circuits.
  arXiv  Detail & Related papers  (2020-06-30T14:52:14Z)
• Topological superconductor from superconducting topological surface states and fault-tolerant quantum computing [6.394072140094434]
  A widely believed chiral $p$-wave superfluid is the Moore-Read state in the $nu=frac52$ fractional quantum Hall effect. Here we report a new mechanism for realizing 2D chiral $p$-wave superconductors on the surface of 3D $s$-wave superconductors.
  arXiv  Detail & Related papers  (2020-03-26T06:07:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.