XRD Component Decomposition

How does AI help me?

This AI-powered module can separate an X-ray diffraction (XRD) pattern of an unknown mixture into multiple components and quantify each phase.

This decomposition does not require any knowledge or phase identification analysis of the sample and can be useful when comparing tens and hundreds of XRD patterns consisting of similar phases.

How does AI-powered XRD profile decomposition work?

This module applies a demensionality-reduction algorithm originally developed for machine learning. The dimensionality-reduction algorithm attempts to reproduce an XRD pattern by combining a few XRD patterns at different weights.

It starts off with randomly guessed phases and gradually increases the number of phases as necessary while refining the weights and trying to fit the experimental XRD pattern each time. It repeats the process, trying thousands of combinations, until the experimental XRD profile is reproduced sufficiently well by a combination of a few components. A user can specify the number of phases or let the algorithm estimate it.

The components can be any crystalline material, including unknown phases, or even amorphous.

When is AI-powered XRD profile decomposition useful?

AI-powered XRD profile decomposition is beneficial when you need to analyze many similar XRD patterns.

For example, in-situ measurements, especially DSC-XRD and time-resolved measurements, can produce hundreds of XRD patterns to analyze. Measurements of a 96-well plate, often used for combinatorial chemistry, can also produce many patterns. When analyzing these data, using the AI-powered profile decomposition can produce phase identification and quantitative analysis results with minimum operator involvement.

Example

An example of similar diffraction patterns is shown below.

The profile decomposition algorithm suggested three phases, including an amorphous phase.

In the decomposition process, each phase is quantified based on its weight.