# US 2026/0301878 A1 · Method and system for determining the concentration of one or more alkaloids in tobacco leave samples

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

- Number: US 2026/0301878 A1
- Document ID: US20260301878A1
- Status: Published application
- Kind: A1
- Application number: 19/477,057
- Filed: 2024-04-19
- Published: 2026-10-01
- Earliest claimed: 2023-04-20
- Assignees: British American Tobacco (Investments) Limited
- Applicants: British American Tobacco (Investments) Limited
- Inventors: Marcelo Caetano Alexandre MARCELO; Maurilio Gustavo NESPECA; Samuel KAISER
- Web page: https://patentgrep.com/patent/US20260301878A1

## CPC

- G16C 20/20: Identification of molecular entities, parts thereof or of chemical compositions
- G01N 21/3563: for analysing solids; Preparation of samples therefor
- G01N 21/359: using near infrared light
- G16C 20/70: Machine learning, data mining or chemometrics
- G01N 2021/8466: {Investigation of vegetal material, e.g. leaves, plants, fruits}
- G01N 2201/1296: using neural networks
- G16C: COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- 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)

## Abstract

A computer-implemented method for detecting a concentration of one or more alkaloids in tobacco target samples using a target analysis technique based on near-infrared spectroscopy is provided, the method comprising providing one or more trained artificial intelligence models obtained or obtainable by training one or more untrained or pre-trained artificial intelligence models using sample information, reference concentration data relating to the one or more alkaloids, and near-infrared reference spectral data obtained or obtainable using the target analysis technique for a plurality of tobacco reference samples; analyzing the tobacco target samples using the target analysis technique providing near-infrared target spectra and preprocessing the near-infrared target spectra to obtain preprocessed near-infrared target spectral data; and deriving the concentration of the one or more alkaloids in the tobacco target samples using the or one of the trained artificial intelligence models and on the basis of the preprocessed near-infrared target spectral data; wherein said analyzing the tobacco target samples includes providing a plurality of the near-infrared target spectra in a common sub-range of the near-infrared wavelength range for each of the tobacco reference samples, wherein said preprocessing the near-infrared target spectra includes averaging said plurality of near-infrared target spectra for each of the tobacco target samples and performing a standard normal variates transformation followed by Savitzky-Golay first derivative and mean centering, and wherein said tobacco target samples include one or more groups of tobacco target samples grouped according to chemical similarity of different tobacco varieties or types, at least one trained artificial intelligence model being provided for each of the groups or tobacco varieties or types therein. A method of providing one or more trained artificial intelligence models, a system and a computer program are provided as well.

## Claims

### Claim 1

A computer-implemented method for detecting a concentration of one or more alkaloids in tobacco target samples using a target analysis technique based on near-infrared spectroscopy, the method comprising:
providing one or more trained artificial intelligence models obtained or obtainable by training one or more untrained or pre-trained artificial intelligence models using sample information, reference concentration data relating to the one or more alkaloids, and near-infrared reference spectral data obtained or obtainable using the target analysis technique for a plurality of tobacco reference samples;
analyzing the tobacco target samples using the target analysis technique providing near-infrared target spectra and preprocessing the near-infrared target spectra to obtain preprocessed near-infrared target spectral data; and
deriving the concentration of the one or more alkaloids in the tobacco target samples using the or one of the trained artificial intelligence models and on the basis of the preprocessed near-infrared target spectral data;
wherein said analyzing the tobacco target samples includes providing a plurality of the near-infrared target spectra in a common sub-range of the near-infrared wavelength range for each of the tobacco reference samples,
wherein said preprocessing the near-infrared target spectra includes averaging said plurality of near-infrared target spectra for each of the tobacco target samples and performing a standard normal variates transformation, and
wherein said tobacco target samples include one or more groups of tobacco target samples of different tobacco varieties or types grouped according to chemical similarity, at least one trained artificial intelligence model being provided for each of the groups or tobacco varieties or types in said groups.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the one or more alkaloids are selected from total alkaloids present in the tobacco target samples and nicotine.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the plurality of near-infrared target spectra averaged for each of the tobacco target samples is three.

### Claim 4 (depends on 1)

The method according to claim 1, wherein said preprocessing further comprises a standard normal variate transformation, followed by Savitzky-Golay first derivative and mean centering.

### Claim 5 (depends on 4)

The method according to claim 4, wherein a window size of fifteen and an order of two is used in forming the first derivative.

### Claim 6 (depends on 1)

The method according to claim 1, wherein the common sub-range of the near-infrared wavelength range is between 947 nm and 1,618 nm.

### Claim 7 (depends on 1)

The method according to claim 1, wherein said groups include at least one of a flue curing and an air curing group.

### Claim 8 (depends on 1)

The method according to claim 1, wherein said analyzing the tobacco target samples includes spectroscopically examining tobacco leaves at a plurality of predetermined sampling positions.

### Claim 9 (depends on 1)

The method according to claim 1, wherein said analyzing the tobacco target samples is performed under defined moisture conditions.

### Claim 10 (depends on 1)

The method according to claim 1, wherein the tobacco target samples comprise one or more green tobacco leaves.

### Claim 11 (depends on 10)

The method according to claim 10, wherein the one or more green tobacco leaves are probed under defined probing conditions.

### Claim 12 (depends on 1)

The method according to claim 1, wherein the method includes partial least squares regression.

### Claim 13 (depends on 1)

The method according to claim 1, wherein the method is performed in a system comprising a near-infrared spectroscopy device and a mobile unit connected or connectable to a server, wherein the one or more trained artificial intelligence models is downloaded from the server to the mobile unit to perform at least said deriving the concentration of the one or more alkaloids in the tobacco target samples.

### Claim 14 (depends on 1)

A method of providing one or more trained artificial intelligence models usable in the method according to claim 1, the method comprising:
providing a plurality of tobacco reference samples and sample information indicating characteristics of the tobacco reference samples;
analyzing the tobacco reference samples for the one or more alkaloids using one or more reference analysis techniques providing reference concentration data;
analyzing each of the tobacco reference samples using the target analysis technique providing near-infrared reference spectra;
preprocessing the near-infrared reference spectra for the tobacco reference samples obtaining preprocessed spectral data; and
training one or more artificial intelligence models using the sample information, the reference concentration data and the preprocessed spectral data obtaining the trained artificial intelligence model;
wherein said analyzing the tobacco reference samples and said preprocessing the near-infrared reference spectra is performed as for the tobacco target samples, and
wherein said tobacco reference samples include one or more groups of tobacco target samples formed by grouping different tobacco types or varieties according to chemical similarity, at least one trained artificial intelligence model being provided for each of the groups or each of the tobacco types or varieties therein.

### Claim 15 (depends on 14)

A trained artificial intelligence model stored on a non-tangible computer-readable medium obtained or obtainable by using the method according to claim 14.

### Claim 16 (depends on 1)

The method according to claim 1, wherein the one or more trained artificial intelligence models is applied to new sample by multiplying a vector of regression coefficients and the preprocessed average spectrum of the sample, generating a target concentration as a result.

### Claim 17 (depends on 1)

A system for detecting a concentration of one or more alkaloids in tobacco target samples using a target analysis technique based on near-infrared spectroscopy, the system being configured to perform a method according to claim 1.

### Claim 18 (depends on 17)

The system according to claim 17, comprising a near-infrared spectroscopy device and a mobile unit connected or connectable to a server, wherein the one or more trained artificial intelligence models is downloadable from the server to the mobile unit and wherein the mobile unit is configured to perform at least said deriving the concentration of the one or more alkaloids in the tobacco target samples.

### Claim 19 (depends on 1)

A computer program with a program code for performing the method according to claim 1 when the computer program is run on a processor.
