# US 2025/0093319 A1 · Detecting wine characteristics from wine samples

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

- Number: US 2025/0093319 A1
- Document ID: US20250093319A1
- Status: Published application
- Kind: A1
- Application number: 18/961,351
- Filed: 2024-11-26
- Published: 2025-03-20
- Earliest claimed: 2022-05-27
- Inventors: Ye Feng
- Web page: https://patentgrep.com/patent/US20250093319A1

## CPC

- G01N 33/146: {containing alcohol}
- G01J 3/28: Investigating the spectrum (using colour filters G01J3/51)
- G01J 3/44: Raman spectrometry; Scattering spectrometry {; Fluorescence spectrometry}
- G01N 21/65: Raman scattering
- G01N 21/658: {enhancement Raman, e.g. surface plasmons}
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/0475: Generative networks
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning
- G06N 3/09: Supervised learning
- G06N 3/096: Transfer learning
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N 20/20: Ensemble learning
- G16C 20/20: Identification of molecular entities, parts thereof or of chemical compositions
- G16C 20/70: Machine learning, data mining or chemometrics
- G01N 2201/1296: using neural networks
- 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)
- G01J: MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY (light sources F21, H01J, H01K, H05B; investigating properties of materials by optical means G01N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G16C: COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE

## Abstract

Methods of predicting perceptual characteristics may include: (a) receiving an optical signal from a sample of a grape product or a wine; (b) extracting features from the optical signal by transforming information in the optical signal to a latent space; and (c) providing the features to a machine learning model that outputs (i) chemical composition information in the grape product or the wine, and/or (ii) the one or more perceptual characteristics of a finished wine produced from the grape product or of the wine. The chemical composition information and/or the perceptual characteristics may pertain to smoke taint.

## Claims

### Claim 1

A method of predicting smoke taint, the method comprising:
receiving an optical signal from a sample of a grape product or a wine, wherein the optical signal comprises a spectrum having characteristics influenced by chemical components of the grape product or the wine;
extracting features from the optical signal by transforming information in the optical signal to a latent space, which latent space has reduced dimensions compared to dimensions of the optical signal; and
providing the features to a machine learning model that provides (i) chemical composition information in the grape product or the wine, wherein the chemical composition information includes information about one or more compounds that are associated smoke taint, and/or (ii) one or more perceptual characteristics of a finished wine produced from the grape product or of the wine, wherein the perceptual characteristics indicate whether the finished wine produced from the grape product or the wine exhibits a smoke taint perceptual characteristic.

### Claim 2 (depends on 1)

The method of claim 1, wherein the sample comprises one or more grapes used to produce the finished wine.

### Claim 3 (depends on 1)

The method of claim 1, wherein the sample comprises must or juice used to produce the finished wine.

### Claim 4 (depends on 1)

The method of claim 1, wherein the sample comprises the wine.

### Claim 5 (depends on 1)

The method of claim 1, further comprising obtaining the optical signal from the sample comprising the grape product or the wine.

### Claim 6 (depends on 1)

The method of claim 1, wherein the optical signal is a signal from Raman spectroscopy performed on the grape product or the wine.

### Claim 7 (depends on 6)

The method of claim 6, wherein Raman spectroscopy is a Surface Enhanced Raman Spectroscopy (SERS).

### Claim 8 (depends on 7)

The method of claim 7, further comprising contacting the sample with a nanoscale material that enhances Raman signals from the sample.

### Claim 9 (depends on 8)

The method of claim 8, further comprising: contacting the sample with multiple nanostructures, and obtaining a Raman signal for each nanostructure and sample combination.

### Claim 10 (depends on 1)

The method of claim 1, wherein the optical signal comprises information from at least 10 wavelengths.

### Claim 11 (depends on 1)

The method of claim 1, further comprising providing information from a portion of a grape plant that is not a grape to the machine learning model, wherein the grape plant produced grapes for the grape product or the wine.

### Claim 12 (depends on 11)

The method of claim 11, wherein the portion of the grape plant comprises a leaf of the grape plant.

### Claim 13 (depends on 1)

The method of claim 1, further comprising providing information from an electronic sensor of volatile organic compounds to the machine learning model.

### Claim 14 (depends on 1)

The method of claim 1, further comprising providing information from infrared, fluorescence, and/or visible spectra of the grape product or the wine to the machine learning model.

### Claim 15 (depends on 1)

The method of claim 1, further comprising providing information about a wine making process for producing the wine or the finished wine to the machine learning model.

### Claim 16 (depends on 15)

The method of claim 15, wherein the information about the wine making process is selected from a group consisting of: grape sources, harvest time, crushing conditions, must handling, time between crushing and fermentation, temperature prior to, during or after fermentation or incubation, incubation period, yeast, inoculum size, additives, pH, substrate concentration, and any combinations thereof.

### Claim 17 (depends on 1)

The method of claim 1, wherein extracting features comprises providing the optical signal to a variational autoencoder or a transformer model trained using training data comprising training optical signals from smoke tainted grape products or wines.

### Claim 18 (depends on 1)

The method of claim 1, wherein the machine learning model is trained using training data comprising training mass spectrometry data obtained from smoke tainted grape products or wines.

### Claim 19 (depends on 18)

The method of claim 18, wherein the training mass spectrometry data are obtained using a technique selected from a group consisting of gas chromatography-mass spectroscopy (GC-MS), gas chromatography-tandem mass spectroscopy (GC-MS-MS), high performance liquid chromatography-mass spectroscopy (HPLC-MS), high performance liquid chromatography-tandem mass spectroscopy (HPLC-MS-MS), high performance liquid chromatography-diode array detector-mass spectroscopy (HPLC-DAD-MS), and any combinations thereof.

### Claim 20 (depends on 18, 19)

The method of claim 18 or 19, wherein the machine learning model provides chemical composition information in the grape product or the wine corresponding to the training mass spectrometry data.

### Claim 21 (depends on 1)

The method of claim 1, further comprising:
producing multiple optical signals from the sample;
extracting features from each of the multiple optical signals; and
combining the features from each of the multiple optical signal to produce one or more combined features of the multiple optical samples.

### Claim 22 (depends on 21)

The method of claim 21, providing the features to the machine learning model comprises providing the combined features of the multiple optical samples to the machine learning model.

### Claim 23 (depends on 1)

The method of claim 1, wherein the machine learning model is a neural network.

### Claim 24 (depends on 1)

The method of claim 1, further comprising preprocessing the optical signal to normalize and/or reduce noise in the optical signal prior to extracting features from the optical signal.

### Claim 25 (depends on 1)

The method of claim 1, wherein the chemical composition information includes information about a catechin, a tannin, an anthocyanin, a quercetin, a guaiacol, a cresol, a syringol, a glycoside of any of the foregoing, and any combination of the foregoing.

### Claim 26 (depends on 1)

The method of claim 1, wherein the one or more compounds that are associated with smoke taint comprise a guaiacol, a cresol, a syringol, a glycoside of any of the foregoing, and any combination of the foregoing.

### Claim 27

A method of training a machine learning model configured to predict smoke taint in a wine, the method comprising:
receiving training data for each of a plurality of samples, each sample comprising a grape product and/or a wine, wherein the training data for each sample comprises (a) an optical signal generated from the sample, and (b) (i) chemical composition information in the grape product, a finished wine produced from the grape product, or the wine, wherein the chemical composition information includes information about one or more compounds that are associated with smoke taint, and/or (ii) one or more perceptual characteristics of the finished wine produced from the grape product or of the wine, wherein the perceptual characteristics indicate whether the finished wine produced from the grape product or the wine exhibits a smoke taint perceptual characteristic;
training a feature extractor using at least a portion of the training data, wherein the feature extractor is trained to extract features from the optical signals generated from the training samples by transforming information in the optical signals to a latent space, which latent space has reduced dimensions compared to dimensions of the optical signals; and
training a machine learning model, using at least a portion of the training data and at least features extracted from the training data by the feature extractor, wherein the machine learning model is trained to predict (i) the chemical composition information in the grape product, the finished wine produced from the grape product, or the wine, and/or (ii) one or more perceptual characteristics of the finished wine produced from the grape product or of the wine.

### Claim 28 (depends on 27)

The method of claim 27, wherein the plurality of samples comprises a plurality of grapes.

### Claim 29 (depends on 27)

The method of claim 27, wherein the plurality of samples comprises must or juice.

### Claim 30 (depends on 27)

The method of claim 27, wherein the plurality of samples comprises a grape product spiked with one or more smoke taint compounds and/or a wine spiked with one or more smoke taint compounds.

### Claim 31 (depends on 27)

The method of claim 27, wherein the optical signals from the samples comprise Raman spectra.

### Claim 32 (depends on 31)

The method of claim 31, wherein the Raman spectra were obtained using a Surface Enhanced Raman Spectroscopy (SERS).

### Claim 33 (depends on 27)

The method of claim 27, wherein the optical signals from the samples each comprise information from at least 10 wavelengths.

### Claim 34 (depends on 27)

The method of claim 27, wherein the training data for each of the plurality of samples further comprises information from a portion of a grape plant that is not a grape, wherein the grape plant produced grapes for the grape product or the wine.

### Claim 35 (depends on 34)

The method of claim 34, wherein the portion of the grape plant comprises a leaf of the grape plant.

### Claim 36 (depends on 27)

The method of claim 27, wherein the training data further comprises information from an electronic sensor of volatile organic compounds.

### Claim 37 (depends on 27)

The method of claim 27, wherein the training data further comprises information from fluorescence spectra, infrared spectra and/or visible spectra of the grape produce or the wine.

### Claim 38 (depends on 27)

The method of claim 27, wherein training the feature extractor comprises training a variational autoencoder or a transformer model using the optical signals generated from the samples.

### Claim 39 (depends on 27)

The method of claim 27, wherein the machine learning model is a neural network.

### Claim 40 (depends on 27)

The method of claim 27, wherein the chemical composition information comprises information about a catechin, a tannin, an anthocyanin, a quercetin, a guaiacol, a cresol, a syringol, a glycoside of any of the foregoing, and any combination of the foregoing.

### Claim 41 (depends on 27)

The method of claim 27, wherein the one or more compounds that cause smoke taint comprise a guaiacol, a-cresol, a syringol, a glycoside of any of the foregoing, and any combination of the foregoing.

### Claim 42

A method of predicting perceptual characteristics, the method comprising:
receiving an optical signal from a sample of a grape product or a wine, wherein the optical signal comprises a spectrum having characteristics influenced by chemical components of the grape product or the wine;
extracting features from the optical signal by transforming information in the optical signal to a latent space, which latent space has reduced dimensions compared to dimensions of the optical signal; and
providing the features to a machine learning model that outputs (i) chemical composition information in the grape product or the wine, wherein the chemical composition information includes information about one or more compounds that are associated with one or more perceptual characteristics, and/or (ii) the one or more perceptual characteristics of a finished wine produced from the grape product or of the wine.

### Claim 43 (depends on 42)

The method of claim 42, wherein the one or more perceptual characteristics comprise a perceptual characteristic selected from the group consisting of a taste, an aroma, a mouthfeel, an appearance, and any combinations thereof.

### Claim 44 (depends on 42)

The method of claim 42, wherein the one or more perceptual characteristics comprise a smoke taint perceptual characteristic.

### Claim 45 (depends on 42)

The method of claim 42, wherein the one or more perceptual characteristics comprise a perceptual characteristic associated with one or more chemical byproducts of an organism, and wherein the chemical composition information comprises information about the one or more chemical byproducts of the organism.

### Claim 46 (depends on 45)

The method of claim 45, wherein the organism comprises Brettanomyces, and wherein the chemical composition information comprises information about 4-ethylphenol, 4-ethylguaiacol, 4-ethylcatechol, and/or 4-propylguaiacol.

### Claim 47 (depends on 45, 46)

The method of claim 45 or 46, further comprising repeating the method for multiple samples obtained at multiple stages in a wine making process.

### Claim 48 (depends on 47)

The method of claim 47, further comprising using the output of the machine learning model at the multiple stages of the wine making process to account for potential variations in the presence or concentration of Brettanomyces during the wine making process.

### Claim 49 (depends on 42)

The method of claim 42, wherein the one or more perceptual characteristics comprise a perceptual characteristic indicating whether or not consumers favorably perceives the finished wine produced from the grape product or the wine.

### Claim 50 (depends on 42)

The method of claim 42, wherein the one or more perceptual characteristics comprise a favorability score indicating how favorably consumers consider the finished wine produced from the grape product or the wine.

### Claim 51 (depends on 42)

The method of claim 42, wherein the one or more perceptual characteristics comprise one or more metrics of the finished wine or a score representing the one or more metrics of the finished wine.

### Claim 52 (depends on 42)

The method of claim 42, wherein the machine learning model is configured to output information selected from a group consisting of: grape variety, terroir details, appellation, vineyard, harvest year, additives, and other characteristics or properties of a finished wine or a grape product, and any combinations thereof.

### Claim 53 (depends on 42)

The method of claim 42, wherein the machine learning model is configured to output a recommendation of one or more wine making process parameters.

### Claim 54 (depends on 53)

The method of claim 53, wherein the one or more wine making process parameters is selected from a group consisting of: grape sources, harvest time, crushing conditions, must handling, time between crushing and fermentation, temperature prior to, during or after fermentation or incubation, incubation period, yeast, inoculum size, additives, pH, substrate concentration, and any combinations thereof.

### Claim 55 (depends on 42)

The method of claim 42, the machine learning model is configured to output a recommendation of a type and/or a parameter of flavor engineering process.

### Claim 56 (depends on 42)

The method of claim 42, wherein the chemical composition information comprises information about a catechin, tannin, anthocyanin, terpinol, linalool, geraniol, α-terpineol, citronelol, nerol, nor-isoprenoid, β-damsascenone, β-ionone, α-ionone, ethyl cinnamate, ethyl dihydrocinnamate, hexanol, Z-3-hexenol, E-2-hexenol, ethanol, fusel alcohol, isobutanol, 2 and 3-methylbutanol, isoamylalcohol, β-phenylethanol, methionol, fusel alcohol acetate, isobutyl acetate, isoamyl acetate, hexyl acetate, phenylethyl acetate, fatty acid, acetic acid, butyric acid, hexanoic acid, octanoic acid, decanoic acid, ethyl acetate, ethyl butyrate, ethyl hexanoate, ethyl octanoate, ethyl decanoate, isobutyric acid, 2-methylbutyric acid, 3-methylbutyric acid, isovaleric acid, ethyl isobutyrate, ethyl 2-methylbutyrate, ethyl 3-methylbutyrate, ethyl isovalerate, carbonyl, lactone, diacetyl, 2,3-pentanedione, acetoine, γ-butyrolactone, ethyl lactate, diethyl succinate, Z-whiskylactone, E-whiskylactone, o and m-cresol, guaiacol, 4-methylguaiacol, eugenol, E-isoeugenol, 2,6-dimethoxyphenol, 4-allyl-2,6-dimethoxyphenol, vanillin, acetovanillone, propiovanillone, ethylvanillate, methylvanillate, furfural, 5-methylfurfural, 4-ethylphenol, 4-ethylguaiacol, 4-propylguaiacol, γ-lactones, γ-octalactone, γ-nonalactone, γ-decalactone, γ-undecalactone, γ-dodecalactone, 4-vinylphenol, 4-vinylguaiacol, and any combination of the foregoing.

### Claim 57 (depends on 42)

The method of claim 42, wherein the sample comprises one or more grapes used to produce the finished wine.

### Claim 58 (depends on 42)

The method of claim 42, wherein the sample comprises must or juice used to produce the finished wine.

### Claim 59 (depends on 42)

The method of claim 42, wherein the sample comprises the wine.

### Claim 60 (depends on 42)

The method of claim 42, further comprising obtaining the optical signal from the sample comprising the grape product or the wine.

### Claim 61 (depends on 42)

The method of claim 42, wherein the optical signal is a signal from Raman spectroscopy performed on the grape product or the wine.

### Claim 62 (depends on 61)

The method of claim 61, wherein Raman spectroscopy is a Surface Enhanced Raman Spectroscopy (SERS).

### Claim 63 (depends on 62)

The method of claim 62, further comprising contacting the sample with a nanoscale material that enhances Raman signals from the sample.

### Claim 64 (depends on 42)

The method of claim 42, further comprising providing information from an electronic sensor of volatile organic compounds to the machine learning model.

### Claim 65 (depends on 42)

The method of claim 42, further comprising providing information from infrared, fluorescence, and/or visible spectra of the grape produce or the wine to the machine learning model.

### Claim 66 (depends on 42)

The method of claim 42, wherein extracting features comprises providing the optical signal to a variational autoencoder or a transformer model trained using training optical signals from training data.

### Claim 67 (depends on 42)

The method of claim 42, wherein the machine learning model is a neural network.

### Claim 68 (depends on 42)

The method of claim 42, wherein extracting features comprises providing the optical signal to a variational autoencoder or a transformer model trained using training data comprising training optical signals from training samples of grape products and/or wines.

### Claim 69 (depends on 42)

The method of claim 42, wherein the machine learning model is trained using training data comprising training mass spectrometry data obtained from training samples of grape products and/or wines.

### Claim 70 (depends on 69)

The method of claim 69, wherein the training mass spectrometry data are obtained using a technique selected from a group consisting of gas chromatography-mass spectroscopy (GC-MS), gas chromatography-tandem mass spectroscopy (GC-MS-MS), high performance liquid chromatography-mass spectroscopy (HPLC-MS), high performance liquid chromatography-tandem mass spectroscopy (HPLC-MS-MS), high performance liquid chromatography-diode array detector-mass spectroscopy (HPLC-DAD-MS), and any combinations thereof.

### Claim 71 (depends on 69, 70)

The method of claim 69 or 70, wherein the machine learning model provides chemical composition information in the grape product or the wine corresponding to the training mass spectrometry data.

### Claim 72 (depends on 42)

The method of claim 42, wherein the machine learning model is trained using training data comprising microbiological information indicating the presence of a microorganism.

### Claim 73 (depends on 72)

The method of claim 72, wherein microbiological information is PCR results indicating the presence of the microorganism.

### Claim 74

A method of training a machine learning model configured to predict perceptual characteristics of a wine, the method comprising:
receiving training data for each of a plurality of samples, each sample comprising a grape product and/or a wine, wherein the training data for each sample comprises (a) an optical signal generated from the sample, and (b) (i) chemical composition information in the grape product, a finished wine produced from the grape product, or the wine, wherein the chemical composition information includes information about one or more compounds that are associated with one or more perceptual characteristics, and/or (ii) the one or more perceptual characteristics of the finished wine produced from the grape product or of the wine;
training a feature extractor using at least a portion of the training data, wherein the feature extractor is trained to extract features from the optical signals generated from the training samples by transforming information in the optical signals to a latent space, which latent space has reduced dimensions compared to dimensions of the optical signals; and
training a machine learning model, using at least a portion of the training data and at least features extracted from the training data by the feature extractor, wherein the machine learning model is trained to predict (i) the chemical composition information in the grape product, the finished wine produced from the grape product, or the wine, and/or (ii) the one or more perceptual characteristics of the finished wine produced from the grape product or of the wine.

### Claim 75 (depends on 74)

The method of claim 74, wherein the one or more perceptual characteristics comprise a perceptual characteristic selected from the group consisting of a taste, an aroma, a mouthfeel, an appearance, and any combinations thereof.

### Claim 76 (depends on 74)

The method of claim 74, wherein the one or more perceptual characteristics comprise a smoke taint perceptual characteristic.

### Claim 77 (depends on 74)

The method of claim 74, wherein the one or more perceptual characteristics comprise a Brettanomyces taint perceptual characteristic.

### Claim 78 (depends on 74)

The method of claim 74, wherein the one or more perceptual characteristics comprise a perceptual characteristic indicating whether or not the finished wine produced from the grape product or the wine is favorably perceived by consumers.

### Claim 79 (depends on 74)

The method of claim 74, wherein the one or more perceptual characteristics comprise a favorability score indicating how favorably the finished wine produced from the grape product or the wine is perceived by consumers.

### Claim 80 (depends on 74)

The method of claim 74, wherein the chemical composition information comprises information about a catechin, tannin, anthocyanin, terpinol, linalool, geraniol, α-terpineol, citronelol, nerol, nor-isoprenoid, β-damsascenone, β-ionone, α-ionone, ethyl cinnamate, ethyl dihydrocinnamate, hexanol, Z-3-hexenol, E-2-hexenol, ethanol, fusel alcohol, isobutanol, 2 and 3-methylbutanol, isoamylalcohol, β-phenylethanol, methionol, fusel alcohol acetate, isobutyl acetate, isoamyl acetate, hexyl acetate, phenylethyl acetate, fatty acid, acetic acid, butyric acid, hexanoic acid, octanoic acid, decanoic acid, ethyl acetate, ethyl butyrate, ethyl hexanoate, ethyl octanoate, ethyl decanoate, isobutyric acid, 2-methylbutyric acid, 3-methylbutyric acid, isovaleric acid, ethyl isobutyrate, ethyl 2-methylbutyrate, ethyl 3-methylbutyrate, ethyl isovalerate, carbonyl, lactone, diacetyl, 2,3-pentanedione, acetoine, γ-butyrolactone, ethyl lactate, diethyl succinate, Z-whiskylactone, E-whiskylactone, o and m-cresol, guaiacol, 4-methylguaiacol, eugenol, E-isoeugenol, 2,6-dimethoxyphenol, 4-allyl-2,6-dimethoxyphenol, vanillin, acetovanillone, propiovanillone, ethylvanillate, methylvanillate, furfural, 5-methylfurfural, 4-ethylphenol, 4-ethylguaiacol, 4-propylguaiacol, γ-lactones, γ-octalactone, γ-nonalactone, γ-decalactone, γ-undecalactone, γ-dodecalactone, 4-vinylphenol, 4-vinylguaiacol, or any combination of the foregoing.

### Claim 81 (depends on 74)

The method of claim 74, wherein the plurality of samples comprises a plurality of grapes.

### Claim 82 (depends on 74)

The method of claim 74, wherein the plurality of samples comprises must or juice.

### Claim 83 (depends on 74)

The method of claim 74, wherein the plurality of samples comprises a grape product spiked with one or more compounds causing the one or more perceptual characteristics and/or a wine spiked with one or more compounds causing the one or more perceptual characteristics.

### Claim 84 (depends on 74)

The method of claim 74, wherein the plurality of samples comprises a grape product spiked with a microbial organism.

### Claim 85 (depends on 84)

The method of claim 84, wherein the microbial organism is Brettanomyces.

### Claim 86 (depends on 74)

The method of claim 74, wherein the optical signals from the samples comprise Raman spectra.

### Claim 87 (depends on 86)

The method of claim 86, wherein the Raman spectra were obtained using a Surface Enhanced Raman Spectroscopy (SERS).

### Claim 88 (depends on 74)

The method of claim 74, wherein the optical signals from the samples each comprise information from at least 10 wavelengths.

### Claim 89 (depends on 74)

The method of claim 74, wherein the training data further comprises information from an electronic sensor of volatile organic compounds.

### Claim 90 (depends on 74)

The method of claim 74, wherein the training data further comprises information from infrared spectra, fluorescence, and/or visible spectra of the grape produce or the wine.

### Claim 91 (depends on 74)

The method of claim 74, wherein training the feature extractor comprises training a variational autoencoder or a transformer model using the optical signals generated from the samples.

### Claim 92 (depends on 74)

The method of claim 74, wherein the machine learning model is a neural network.

### Claim 93

A system for predicting perceptual characteristics of wine, the system comprising:
a processor and memory configured to:
receive an optical signal from a sample of a grape product or a wine, wherein the optical signal comprises a spectrum having characteristics influenced by chemical components of the grape product or the wine;
extract features from the optical signal by transforming information in the optical signal to a latent space, which latent space has reduced dimensions compared to dimensions of the optical signal; and
provide the features to a machine learning model that outputs (i) chemical composition information in the grape product or the wine, wherein the chemical composition information includes information about one or more compounds that are associated with one or more perceptual characteristics, and/or (ii) the one or more perceptual characteristics of a finished wine produced from the grape product or of the wine.

### Claim 94 (depends on 93)

The system of claim 93, wherein the one or more perceptual characteristics comprise a perceptual characteristic selected from the group consisting of a taste, an aroma, a mouthfeel, an appearance, and any combinations thereof.

### Claim 95 (depends on 93)

The system of claim 93, wherein the one or more perceptual characteristics comprise a smoke taint perceptual characteristic.

### Claim 96 (depends on 93)

The system of claim 93, wherein the one or more perceptual characteristics comprise a perceptual characteristic associated with one or more chemical byproducts of an organism, and wherein the chemical composition information comprises information about the one or more chemical byproducts of the organism.

### Claim 97 (depends on 96)

The system of claim 96, wherein the organism comprises Brettanomyces, and wherein the chemical composition information comprises information about 4-ethylphenol, 4-ethylguaiacol, 4-ethylcatechol, and/or 4-propylguaiacol.

### Claim 98 (depends on 93)

The system of claim 93, wherein the one or more perceptual characteristics comprise one or more metrics of the finished wine or a score representing the one or more metrics of the finished wine.

### Claim 99 (depends on 93)

The system of claim 93, wherein the machine learning model is configured to output a recommendation of one or more wine making process parameters.

### Claim 100 (depends on 93)

The system of claim 93, further comprising a Raman spectrometer.

### Claim 101 (depends on 93)

The system of claim 93, further comprising an electronic sensor of volatile organic compounds.

### Claim 102 (depends on 93)

The system of claim 93, wherein the processor and memory are configured to extract the features by providing the optical signal to a variational autoencoder or a transformer model trained using training optical signals from training data.

### Claim 103 (depends on 93)

The system of claim 93, wherein the machine learning model is a neural network.

### Claim 104 (depends on 93)

The system of claim 93, wherein the processor and memory are configured to extract the features by providing the optical signal to a variational autoencoder or a transformer model trained using training data comprising training optical signals from training samples of grape products and/or wines.

### Claim 105 (depends on 93)

The system of claim 93, wherein the machine learning model was trained using training data comprising training mass spectrometry data obtained from training samples of grape products and/or wines.

### Claim 106

A system for training a machine learning model configured to predict perceptual characteristics of a wine, the system comprising:
a processor and memory configured to:
receive training data for each of a plurality of samples, each sample comprising a grape product and/or a wine, wherein the training data for each sample comprises (a) an optical signal generated from the sample, and (b) (i) chemical composition information in the grape product, a finished wine produced from the grape product, or the wine, wherein the chemical composition information includes information about one or more compounds that are associated with one or more perceptual characteristics, and/or (ii) the one or more perceptual characteristics of the finished wine produced from the grape product or of the wine;
train a feature extractor using at least a portion of the training data, wherein the feature extractor is trained to extract features from the optical signals generated from the training samples by transforming information in the optical signals to a latent space, which latent space has reduced dimensions compared to dimensions of the optical signals; and
train a machine learning model, using at least a portion of the training data and at least features extracted from the training data by the feature extractor, wherein the machine learning model is trained to predict (i) the chemical composition information in the grape product, the finished wine produced from the grape product, or the wine, and/or (ii) the one or more perceptual characteristics of the finished wine produced from the grape product or of the wine.

### Claim 107 (depends on 106)

The system of claim 106, wherein the one or more perceptual characteristics comprise a perceptual characteristic selected from the group consisting of a taste, an aroma, a mouthfeel, an appearance, and any combinations thereof.

### Claim 108 (depends on 106)

The system of claim 106, wherein the one or more perceptual characteristics comprise a smoke taint perceptual characteristic.

### Claim 109 (depends on 106)

The system of claim 106, wherein the one or more perceptual characteristics comprise a Brettanomyces taint perceptual characteristic.

### Claim 110 (depends on 106)

The system of claim 106, wherein the chemical composition information comprises information about a catechin, tannin, anthocyanin, terpinol, linalool, geraniol, α-terpineol, citronelol, nerol, nor-isoprenoid, β-damsascenone, β-ionone, α-ionone, ethyl cinnamate, ethyl dihydrocinnamate, hexanol, Z-3-hexenol, E-2-hexenol, ethanol, fusel alcohol, isobutanol, 2 and 3-methylbutanol, isoamylalcohol, β-phenylethanol, methionol, fusel alcohol acetate, isobutyl acetate, isoamyl acetate, hexyl acetate, phenylethyl acetate, fatty acid, acetic acid, butyric acid, hexanoic acid, octanoic acid, decanoic acid, ethyl acetate, ethyl butyrate, ethyl hexanoate, ethyl octanoate, ethyl decanoate, isobutyric acid, 2-methylbutyric acid, 3-methylbutyric acid, isovaleric acid, ethyl isobutyrate, ethyl 2-methylbutyrate, ethyl 3-methylbutyrate, ethyl isovalerate, carbonyl, lactone, diacetyl, 2,3-pentanedione, acetoine, γ-butyrolactone, ethyl lactate, diethyl succinate, Z-whiskylactone, E-whiskylactone, o and m-cresol, guaiacol, 4-methylguaiacol, eugenol, E-isoeugenol, 2,6-dimethoxyphenol, 4-allyl-2,6-dimethoxyphenol, vanillin, acetovanillone, propiovanillone, ethylvanillate, methylvanillate, furfural, 5-methylfurfural, 4-ethylphenol, 4-ethylguaiacol, 4-propylguaiacol, γ-lactones, γ-octalactone, γ-nonalactone, γ-decalactone, γ-undecalactone, γ-dodecalactone, 4-vinylphenol, 4-vinylguaiacol, or any combination of the foregoing.

### Claim 111 (depends on 106)

The system of claim 106, wherein the plurality of samples comprises a grape product spiked with one or more compounds causing the one or more perceptual characteristics and/or a wine spiked with one or more compounds causing the one or more perceptual characteristics.

### Claim 112 (depends on 106)

The system of claim 106, wherein the plurality of samples comprises a grape product spiked with a microbial organism.

### Claim 113 (depends on 106)

The system of claim 106, wherein the optical signals from the samples comprise Raman spectra.

### Claim 114 (depends on 106)

The system of claim 106, wherein the optical signals from the samples each comprise information from at least 10 wavelengths.

### Claim 115 (depends on 106)

The system of claim 106, wherein the training data further comprises information from infrared spectra, fluorescence, and/or visible spectra of the grape produce or the wine.

### Claim 116 (depends on 106)

The method of claim 106, wherein the processor and memory are configured to train the feature extractor by training a variational autoencoder or a transformer model using the optical signals generated from the samples.

### Claim 117 (depends on 106)

The system of claim 106, wherein the machine learning model is a neural network.
