2.3.3.3.17. NXapm_compositionspace_results

Status:

application definition, extends NXobject

Description:

Application definition for results of the CompositionSpace tool used in atom pro ...

Application definition for results of the CompositionSpace tool used in atom probe.

This is an application definition for the common NFDI-MatWerk/FAIRmat infrastructure use case IUC09 that explores how to improve the organization and results storage of the CompositionSpace software using NeXus.

Symbols:

The symbols used in the schema to specify e.g. dimensions of arrays.

grid_dim: The dimensionality of the grid.

n_voxels: Total number of voxels.

n_ions: Total number of ions in the reconstructed dataset.

Groups cited:

NXcg_grid, NXcs_profiling, NXdata, NXentry, NXidentifier, NXion, NXobject, NXprocess, NXprogram, NXserialized, NXuser

Structure:

ENTRY: (required) NXentry

definition: (required) NX_CHAR ⤆

Obligatory value: NXapm_compositionspace_results

@version: (optional) NX_CHAR ⤆

analysis_identifier: (recommended) NX_UINT

programID: (required) NXprogram

program: (required) NX_CHAR ⤆

@version: (required) NX_CHAR ⤆

@url: (optional) NX_CHAR ⤆

IDENTIFIER: (optional) NXidentifier

config: (required) NXserialized

Configuration file that was used in this analysis.

type: (optional) NX_CHAR ⤆

path: (required) NX_CHAR ⤆

algorithm: (recommended) NX_CHAR ⤆

checksum: (recommended) NX_CHAR ⤆

USER: (optional) NXuser ⤆

voxelization: (optional) NXprocess ⤆

Step during which the point cloud is discretized to compute element-specific ...

Step during which the point cloud is discretized to compute element-specific composition fields. Iontypes are atomically decomposed to correctly account for the multiplicity of each element that was ranged for each ion.

Using a discretization grid that is larger than the average distance between reconstructed ion positions reduces computational costs. This is the key idea of the CompositionSpace tool compared to other methods used in atom probe for characterizing microstructural features using the ion position data directly.

sequence_index: (required) NX_POSINT ⤆

Obligatory value: 1

weight: (required) NX_NUMBER (Rank: 1, Dimensions: [n_voxels]) {units=NX_UNITLESS}

Total number of weight (counts for discretization with a rectangular trans ...

Total number of weight (counts for discretization with a rectangular transfer function) for the occupancy of each voxel with atoms.

cg_grid: (required) NXcg_grid

dimensionality: (required) NX_POSINT {units=NX_UNITLESS} ⤆

Obligatory value: 3

cardinality: (required) NX_POSINT {units=NX_UNITLESS} ⤆

origin: (required) NX_NUMBER (Rank: 1, Dimensions: [grid_dim]) {units=NX_LENGTH} ⤆

symmetry: (required) NX_CHAR ⤆

Obligatory value: cubic

cell_dimensions: (required) NX_NUMBER (Rank: 1, Dimensions: [grid_dim]) {units=NX_LENGTH} ⤆

extent: (required) NX_POSINT (Rank: 1, Dimensions: [grid_dim]) {units=NX_UNITLESS}

identifier_offset: (required) NX_INT {units=NX_UNITLESS} ⤆

position: (required) NX_NUMBER (Rank: 2, Dimensions: [n_voxels, grid_dim]) {units=NX_LENGTH} ⤆

Position of each cell in Euclidean space.

coordinate: (required) NX_INT (Rank: 2, Dimensions: [n_voxels, grid_dim]) {units=NX_DIMENSIONLESS} ⤆

Discrete coordinate of each voxel.

voxel_identifier: (required) NX_UINT (Rank: 1, Dimensions: [n_ions]) {units=NX_UNITLESS}

For each ion, the identifier of the voxel into which the ion binned.

elementID: (required) NXion

name: (required) NX_CHAR ⤆

Chemical symbol of the element from the periodic table.

weight: (required) NX_NUMBER (Rank: 1, Dimensions: [n_voxels]) {units=NX_UNITLESS}

Element-specific weight (counts for discretization with a rectangular tr ...

Element-specific weight (counts for discretization with a rectangular transfer function) for the occupancy of each voxel with atoms of this element.

autophase: (optional) NXprocess ⤆

Optional step during which the subsequent segmentation step is prepared to ...

Optional step during which the subsequent segmentation step is prepared to improve the segmentation.

sequence_index: (required) NX_POSINT ⤆

Obligatory value: 2

result: (required) NXdata

@signal: (required) NX_CHAR ⤆

@axes: (required) NX_CHAR ⤆

@AXISNAME_indices: (required) NX_CHAR

title: (recommended) NX_CHAR ⤆

axis_feature_identifier: (required) NX_UINT (Rank: 1, Dimensions: [i]) {units=NX_DIMENSIONLESS}

Element identifier stored sorted in descending order of feature importance.

@long_name: (required) NX_CHAR

Axis caption

axis_feature_importance: (required) NX_FLOAT (Rank: 1, Dimensions: [i]) {units=NX_DIMENSIONLESS}

Element relative feature importance stored sorted in descending order of ...

Element relative feature importance stored sorted in descending order of feature importance.

@long_name: (required) NX_CHAR

Axis caption

segmentation: (optional) NXprocess ⤆

Step during which the voxel set is segmented into voxel sets with different ...

Step during which the voxel set is segmented into voxel sets with different chemical composition.

pca: (required) NXprocess

PCA in the chemical space (essentially composition correlation analyses).

sequence_index: (required) NX_POSINT ⤆

Any of these values: 2 | 3

result: (required) NXdata

@signal: (required) NX_CHAR ⤆

@axes: (required) NX_CHAR ⤆

@AXISNAME_indices: (required) NX_CHAR

title: (recommended) NX_CHAR ⤆

axis_explained_variance: (required) NX_FLOAT (Rank: 1, Dimensions: [i]) {units=NX_DIMENSIONLESS}

Explained variance values

axis_pca_dimension: (required) NX_UINT (Rank: 1, Dimensions: [i]) {units=NX_UNITLESS}

Elements identifier matching those from ENTRY/voxelization/elementID a ...

Elements identifier matching those from ENTRY/voxelization/elementID as the principal component analysis.

ic_opt: (required) NXprocess

Information criterion minimization.

sequence_index: (required) NX_POSINT ⤆

Any of these values: 3 | 4

cluster_analysisID: (required) NXprocess

Results of the Gaussian mixture analysis for n_components equal to n_ic_cluster.

n_ic_cluster: (required) NX_UINT {units=NX_UNITLESS}

n_components argument of the Gaussian mixture model.

y_pred: (required) NX_UINT (Rank: 1, Dimensions: [n_voxels]) {units=NX_UNITLESS}

y_pred return values of the computation.

result: (required) NXdata

Information criterion as a function of number of n_ic_cluster aka dimensions.

@signal: (required) NX_CHAR ⤆

@axes: (required) NX_CHAR ⤆

@AXISNAME_indices: (required) NX_CHAR

title: (recommended) NX_CHAR ⤆

axis_aic: (recommended) NX_FLOAT (Rank: 1, Dimensions: [i]) {units=NX_ANY}

Akaike information criterion values

axis_bic: (required) NX_FLOAT (Rank: 1, Dimensions: [i]) {units=NX_UNITLESS}

Bayes information criterion values

axis_dimension: (required) NX_UINT (Rank: 1, Dimensions: [i]) {units=NX_UNITLESS}

Actual n_ic_cluster values used

clustering: (optional) NXprocess ⤆

Step during which the chemically segmented voxel sets are analyzed for their ...

Step during which the chemically segmented voxel sets are analyzed for their spatial organization into different spatial clusters of voxels in the same chemical set but representing individual object not-necessarily watertight or topologically closed objects built from individual voxels.

sequence_index: (required) NX_POSINT ⤆

Any of these values: 4 | 5

ic_opt: (required) NXobject

Respective DBScan clustering result for each segmentation/ic_opt case.

cluster_analysisID: (optional) NXprocess

dbscanID: (required) NXprocess

epsilon: (required) NX_FLOAT {units=NX_LENGTH}

The maximum distance between voxel pairs in a neighborhood to be con ...

The maximum distance between voxel pairs in a neighborhood to be considered connected.

min_samples: (required) NX_UINT {units=NX_UNITLESS}

The number of voxels in a neighborhood for a voxel to be considered ...

The number of voxels in a neighborhood for a voxel to be considered as a core point.

label: (required) NX_INT (Rank: 1, Dimensions: [k]) {units=NX_UNITLESS}

Raw label return values

voxel: (required) NX_UINT (Rank: 1, Dimensions: [n_voxels]) {units=NX_UNITLESS}

Voxel identifier ...

Voxel identifier

Using these identifiers correlated element-wise with the values in the label array specifies for which voxel in the grid clusters from this process were found.

profiling: (optional) NXcs_profiling

current_working_directory: (recommended) NX_CHAR ⤆

start_time: (recommended) NX_DATE_TIME ⤆

end_time: (recommended) NX_DATE_TIME ⤆

total_elapsed_time: (required) NX_NUMBER ⤆

Hypertext Anchors

List of hypertext anchors for all groups, fields, attributes, and links defined in this class.

NXDL Source:

https://github.com/FAIRmat-NFDI/nexus_definitions/tree/fairmat/contributed_definitions/NXapm_compositionspace_results.nxdl.xml