A machine learning route between band mapping and band structure
arXiv:2005.10210 · doi:10.1038/s43588-022-00382-2
Abstract
Electronic band structure (BS) and crystal structure are the two complementary identifiers of solid state materials. While convenient instruments and reconstruction algorithms have made large, empirical, crystal structure databases possible, extracting quasiparticle dispersion (closely related to BS) from photoemission band mapping data is currently limited by the available computational methods. To cope with the growing size and scale of photoemission data, we develop a pipeline including probabilistic machine learning and the associated data processing, optimization and evaluation methods for band structure reconstruction, leveraging theoretical calculations. The pipeline reconstructs all 14 valence bands of a semiconductor and shows excellent performance on benchmarks and other materials datasets. The reconstruction uncovers previously inaccessible momentum-space structural information on both global and local scales, while realizing a path towards integration with materials science databases. Our approach illustrates the potential of combining machine learning and domain knowledge for scalable feature extraction in multidimensional data.
References in corpus (34)
- Restoring the density-gradient expansion for exchange in solids and surfaces
- Generalized gradient approximation for solids and their surfaces
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Angle-resolved photoemission spectroscopy of the cuprate superconductors
- k.p theory for two-dimensional transition metal dichalcogenide semiconductors
- Band structure diagram paths based on crystallography
- Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems
- Data-driven materials science: status, challenges and perspectives
- The GW compendium: A practical guide to theoretical photoemission spectroscopy
- Direct observation of spin-polarised bulk bands in an inversion-symmetric semiconductor
- Chiral Topological Semimetal with Multifold Band Crossings and Long Fermi arcs
- A precise method for visualizing dispersive features in image plots
- HORACE: software for the analysis of data from single crystal spectroscopy experiments at time-of-flight neutron instruments
- FAIR data enabling new horizons for materials research
- Ubiquitous formation of bulk Dirac cones and topological surface states from a single orbital manifold in transition-metal dichalcogenides
- Exciton Polaritons in a Two-Dimensional Lieb Lattice with Spin-Orbit Coupling
- Paradigm shift in electron-based crystallography via machine learning
- 103-Compound Band Structure Benchmark of Post-SCF Spin-Orbit Coupling Treatments in Density-Functional Theory
- Bare electron dispersion from photoemission experiments
- Self-consistent self-energy analysis of photoemission data
- Double resonance Raman modes in mono- and few-layer MoTe
- Angle-resolved photoemission spectroscopy
- Time- and angle-resolved photoemission spectroscopy of solids in the extreme ultraviolet at 500 kHz repetition rate
- Multidimensional Contrast Limited Adaptive Histogram Equalization
- Fully Anharmonic, Non-Perturbative Theory of Vibronically Renormalized Electronic Band Structures
- Deep learning-based statistical noise reduction for multidimensional spectral data
- Tuning time and energy resolution in time-resolved photoemission spectroscopy with nonlinear crystals
- Nanoscale patterning of quasiparticle band alignment
- Super Resolution Convolutional Neural Network for Feature Extraction in Spectroscopic Data
- Visualizing dispersive features in 2D image via minimum gradient method
- Accessing the spectral function in a current-carrying device
- Symmetry-guided nonrigid registration: the case for distortion correction in multidimensional photoemission spectroscopy
- An open-source, end-to-end workflow for multidimensional photoemission spectroscopy
- Deconstruction of Resolution Effects in Angle-Resolved Photoemission