Dataset Information

A machine learning route between band mapping and band structure.

ABSTRACT: The electronic band structure and crystal structure are the two complementary identifiers of solid-state materials. Although convenient instruments and reconstruction algorithms have made large, empirical, crystal structure databases possible, extracting the quasiparticle dispersion (closely related to band structure) from photoemission band mapping data is currently limited by the available computational methods. To cope with the growing size and scale of photoemission data, here 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.

SUBMITTER: Xian RP

PROVIDER: S-EPMC10766556 | biostudies-literature | 2023 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A machine learning route between band mapping and band structure.

Xian R Patrick RP Stimper Vincent V Zacharias Marios M Dendzik Maciej M Dong Shuo S Beaulieu Samuel S Schölkopf Bernhard B Wolf Martin M Rettig Laurenz L Carbogno Christian C Bauer Stefan S Ernstorfer Ralph R

Nature computational science 20221230 1

The electronic band structure and crystal structure are the two complementary identifiers of solid-state materials. Although convenient instruments and reconstruction algorithms have made large, empirical, crystal structure databases possible, extracting the quasiparticle dispersion (closely related to band structure) from photoemission band mapping data is currently limited by the available computational methods. To cope with the growing size and scale of photoemission data, here we develop a p ...[more]

PMID: 38177954

Similar Datasets

Project description:BackgroundAtrial fibrillation (AF) can be maintained by localized intramural reentrant drivers. However, AF driver detection by clinical surface-only multielectrode mapping (MEM) has relied on subjective interpretation of activation maps. We hypothesized that application of machine learning to electrogram frequency spectra may accurately automate driver detection by MEM and add some objectivity to the interpretation of MEM findings.MethodsTemporally and spatially stable single AF drivers were mapped simultaneously in explanted human atria (n=11) by subsurface near-infrared optical mapping (NIOM; 0.3 mm2 resolution) and 64-electrode MEM (higher density or lower density with 3 and 9 mm2 resolution, respectively). Unipolar MEM and NIOM recordings were processed by Fourier transform analysis into 28 407 total Fourier spectra. Thirty-five features for machine learning were extracted from each Fourier spectrum.ResultsTargeted driver ablation and NIOM activation maps efficiently defined the center and periphery of AF driver preferential tracks and provided validated annotations for driver versus nondriver electrodes in MEM arrays. Compared with analysis of single electrogram frequency features, averaging the features from each of the 8 neighboring electrodes, significantly improved classification of AF driver electrograms. The classification metrics increased when less strict annotation, including driver periphery electrodes, were added to driver center annotation. Notably, f1-score for the binary classification of higher-density catheter data set was significantly higher than that of lower-density catheter (0.81±0.02 versus 0.66±0.04, P<0.05). The trained algorithm correctly highlighted 86% of driver regions with higher density but only 80% with lower-density MEM arrays (81% for lower-density+higher-density arrays together).ConclusionsThe machine learning model pretrained on Fourier spectrum features allows efficient classification of electrograms recordings as AF driver or nondriver compared with the NIOM gold-standard. Future application of NIOM-validated machine learning approach may improve the accuracy of AF driver detection for targeted ablation treatment in patients.

Project description:AimCoronary interventions are increasingly being performed via the radial rather than femoral route because of the lower complication rate. Compression devices such as the TR band are used to achieve hemostasis after the procedure. At present, there are no clear protocols for the deflation of the band. In this study we compared two protocols (early deflation with increased intervals vs. late deflation with smaller intervals) in terms of total time to band removal and complications, and patient and staff satisfaction.MethodsAll patients who underwent a transradial coronary procedure and had a TR band fitted were enrolled into the study. The TR band was applied using the patent hemostasis method (2 ml air pushed in after the radial pulse appears on pulse oximetry after full occlusion with 16 ml air). Patients were randomly assigned to either protocol. Protocol 1 involved removal of 2 ml of air starting 1 hour after the sheath removal and then removal of 2 ml every 30 minutes until the band came off. Protocol 2 involved removal of 4 ml of air 2 hours after the sheath removal and then further 4 ml of air every 15 minutes until the band came off. Patient and staff satisfaction was measured with a visual analogue scale.ResultsA total of 174 patients were recruited (mean age, 60 ± 11 years; 127 male, 47 female). The baseline characteristics including total heparin dose and type of procedure, in the two arms were the same. Protocol 2 (n = 84) was associated with a significantly lower time to TR band removal as compared to protocol 1 (n = 90; 201 ± 43 min vs. 274 ± 54 min; p < 0.001). There was no difference in complications such as bleeding or hematoma formation between the two groups. Patient satisfaction was the same between the two groups. However, the staff preferred protocol 1 (p = 0.01).ConclusionA protocol of delayed initiation of TR band deflation followed by quick deflations is associated with a lower time to band removal with no increase in bleeding complications or patient satisfaction. However, the staff preferred longer intervals between deflations.

Dataset Information

A machine learning route between band mapping and band structure.

Publications

A machine learning route between band mapping and band structure.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets