# US 2021/0341400 A1 · Systems and methods for interpreting high energy interactions

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0341400 A1
- Document ID: US20210341400A1
- Status: Published application
- Kind: A1
- Application number: 17/282,206
- Filed: 2019-10-04
- Published: 2021-11-04
- Earliest claimed: 2018-10-04
- Assignees: Decision Tree, LLC
- Applicants: Decision Tree, LLC
- Inventors: Brandon Lee Goodchild Drake
- Web page: https://patentgrep.com/patent/US20210341400A1

## CPC

- G01N 23/223: by irradiating the sample with X-rays or gamma-rays and by measuring X-ray fluorescence
- G01N 23/2076: {for spectrometry, i.e. using an analysing crystal, e.g. for measuring X-ray fluorescence spectrum of a sample with wavelength-dispersion, i.e. WDXFS}
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F 18/24: Classification techniques
- G06N 20/00: Machine learning
- G06N 20/20: Ensemble learning
- G01N 21/33: using ultraviolet light (G01N21/39 takes precedence)
- G01N 21/35: using infrared light (G01N21/39 takes precedence)
- G01N 21/55: Specular reflectivity
- G01N 21/64: Fluorescence; Phosphorescence
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Systems and methods for interpreting high-energy interactions on a sample are described in this application. In particular, this application describes an analysis method that comprises impinging radiation from a source on an analyte, detecting the energy interactions resulting from the impinging radiation using a radiation detector, adjusting the signal from the radiation detector using a machine learning module to emphasize specific parts of the detector signal, training the machine learning module in a supervised or unsupervised manner, producing quantitative and qualitative models using the machine leaning module, and then applying the machine learning module to additional energy interactions. The signal received by the detector can be preprocessed to emphasize specific parts of the detector signal, which is then mapped to a machine learning module for training in a supervised or unsupervised manner. The quantitative and qualitative models derived from this training can be applied to new detector inputs from the same or similar instruments. Other embodiments are described.

## Claims

### Claim 1

An analysis method, comprising:
impinging radiation from a source on an analyte;
detecting energy interactions resulting from the impinging radiation using a radiation detector, wherein the radiation detector produces a signal indicative of the detected energy interactions;
adjusting the signal from the radiation detector using a machine learning module to emphasize specific parts of the signal;
training the machine learning module in a supervised or unsupervised manner;
producing quantitative and qualitative models using the machine leaning module; and
applying the machine learning module to additional energy interactions.

### Claim 2 (depends on 1)

The method of claim 1, wherein the machine learning module uses existing measurements, wherein the existing measurements comprise compositional data about the analyte though empirical measurements or estimated values, membership of the analyte in a class, or a known energy peak for a material of the analyte.

### Claim 3 (depends on 1)

The method of claim 1, wherein the signal is determined by a counting mechanism within the radiation detector that provides data in a continuous interval, which can be used either in a full or summarized form by the machine learning module.

### Claim 4 (depends on 1)

The method of claim 1, further comprising a normalization or data pre-processing step that adjusts detector counts to highlight distinctive features for input mapping into the machine learning module.

### Claim 5 (depends on 1)

The method of claim 1, wherein the machine-learning module uses one or more algorithms to identify relationships in the signal of the detector, wherein the relationships in the signal of the detector comprise random forests, gradient boosting, support vector machines, neural networks, or k-nearest neighbors.

### Claim 6 (depends on 1)

The method of claim 1, wherein the machine learning module provides an output having fluorescent peaks that are guided by relationships within the signal from the radiation detector.

### Claim 7

(canceled)

### Claim 8 (depends on 1)

The method of claim 1, wherein detecting energy interactions resulting from the impinging radiation using a radiation detector; wherein the machine learning module is trained in a supervised manner, wherein the radiation detector is a first radiation detector, and wherein information from at least a second radiation detector used as a part of supervised training of the machine learning module.

### Claim 9 (depends on 1)

The method of claim 1, wherein the radiation comprises photons, and wherein the photons have ionizing effects on the analyte.

### Claim 10 (depends on 9)

The method of claim 9, wherein the signal of the detector that is input into the machine learning module is indicative of photon-fermion interactions that are not the product of ionization.

### Claim 11

(canceled)

### Claim 12 (depends on 1)

The method of claim 1, wherein the additional energy interactions result from impinging radiation on an analyte, and wherein the method further comprises applying the quantitative and qualitative models during analysis of the additional energy interactions.

### Claim 13 (depends on 1)

The method of claim 1, wherein the radiation comprises charged particles, and wherein the charged particles include photons, electrons, or protons with the ability to ionize the analyte.

### Claim 14

An analysis method, comprising:
using a radiation detector to detect energy interactions resulting from radiation impinging on an analyte, wherein the radiation detector produces a signal indicative of the detected energy interactions;
adjusting the signal from the radiation detector using a machine learning module to emphasize specific parts of the signal;
training the machine learning module in a supervised or unsupervised manner;
producing quantitative and qualitative models using the machine leaning module; and
applying the machine learning module to additional energy interactions.

### Claim 15

(canceled)

### Claim 16

(canceled)

### Claim 17

An analysis system, comprising:
a radiation source;
a radiation detector; and
a machine learning module configured to:
receive a signal from the radiation detector, the signal being indicative of detected energy interactions from radiation impinging on an analyte;
adjust the signal to emphasize specific parts of the signal;
train itself in a supervised or unsupervised manner; and
produce quantitative and qualitative models.

### Claim 18 (depends on 17)

The analysis system of claim 17, wherein the machine leaning module is further configured to apply the quantitative and qualitative models to additional energy interactions.

### Claim 19

(canceled)

### Claim 20

(canceled)

### Claim 21

(canceled)

### Claim 22

(canceled)

### Claim 23

(canceled)

### Claim 24

(canceled)

### Claim 25 (depends on 1)

The method of claim 1, wherein the source is an X-ray source, and wherein the radiation detector is an X-ray detector.

### Claim 26 (depends on 25)

The method of claim 25, wherein signal of the X-ray detector is indicative of the fluorescent X-ray emitted from the analyte, and wherein the machine learning module determines a chemistry of the analyte.

### Claim 27 (depends on 1)

The method of claim 1, wherein the signal is indicative of fluorescence peaks, background radiation scatter, coherent (Bragg) scattering, inelastic (Compton) scattering, or elastic (Rayleigh) scattering.

### Claim 28 (depends on 27)

The method of claim 27, wherein the machine learning module provides an output showing energy spectra of elements that are present in the analyte.

### Claim 28 (depends on 28)

The method of claim 28, wherein the machine learning module provides the output to a remote

### Claim 29 (depends on 12)

The method of claim 12, wherein the radiation detector that produces the signal is a first radiation detector, and wherein the additional energy interactions are detected by a second radiation detector that produces a second signal indicative of the additional energy interactions.

### Claim 30 (depends on 18)

The analysis system of claim 18, wherein the radiation source is an X-ray source, and wherein the radiation detector is an X-ray detector.
