pith. sign in

arxiv: 2509.21556 · v2 · submitted 2025-09-25 · 💻 cs.CE

Artificial Intelligence for Food Innovation

Bianca Datta , Markus J. Buehler , Yvonne Chow , Kristina Gligoric , Dan Jurafsky , David L. Kaplan , Rodrigo Ledesma-Amaro , Giorgia Del Missier
show 9 more authors
Lisa Neidhardt Karim Pichara Benjamin Sanchez-Lengeling Miek Schlangen Skyler R. St. Pierre Ilias Tagkopoulos Anna Thomas Nicholas J. Watson Ellen Kuhl
This is my paper

Pith reviewed 2026-05-18 13:32 UTC · model grok-4.3

classification 💻 cs.CE
keywords artificial intelligencefood innovationsustainable proteinsmachine learningclosed-loop designsensory sciencefermentationplant-based foods
0
0 comments X

The pith

AI links molecular composition to functional performance and sensory outcomes in food systems.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper claims that artificial intelligence can connect molecular details in foods to how they function and taste, turning slow trial-and-error innovation into faster, predictive design. This matters because global food production must deliver better nutrition with far lower environmental costs, yet current methods stay fragmented and empirical. The authors treat sustainable proteins from plants, fermentation, and cultivation as a key test case for closed-loop AI systems that handle everything from ingredient creation to recipe generation. They review current applications across formulation, texture, sensory analysis, and manufacturing while outlining priorities such as embedding food science knowledge into machine learning and creating automated discovery labs.

Core claim

Artificial intelligence offers a transformative path to link molecular composition to functional performance, connect chemical structure to sensory outcomes, and accelerate cross-disciplinary innovation across the production pipeline. While broadly applicable to food systems, we focus on sustainable proteins as a high-impact testbed for AI-driven closed-loop design. We review the applications, opportunities, and challenges of AI for Food as an emerging discipline that integrates ingredient design, formulation development, fermentation and production, texture analysis, sensory science, manufacturing, and recipe generation. We identify four priorities: advancing scientific machine learning wit

What carries the argument

AI-driven closed-loop design that treats food as a programmable biomaterial and embeds domain knowledge from food science to connect structure to performance and sensory results.

If this is right

  • Food innovation shifts from empirical trial and error to predictive, design-driven processes.
  • Scientific machine learning incorporates domain priors from food science for better ingredient and formulation design.
  • Self-driving laboratories automate discovery and testing across fermentation, production, and sensory evaluation.
  • Deep reasoning models integrate data on nutrition, sustainability, texture, and sensory qualities in one system.
  • Responsible AI use across the food pipeline accelerates the shift to sustainable food systems for human and planetary health.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same structure-to-function mapping could apply to non-protein food components such as starches or lipids to widen sustainability gains.
  • Success here might require new shared data standards so different food research groups can feed models without building everything from scratch.
  • Automated labs developed for food could transfer to related material design problems in areas like biodegradable packaging or personalized nutrition.
  • Real-world production trials would test whether the closed-loop predictions hold when scaled beyond small lab batches.

Load-bearing premise

Existing AI techniques combined with food science knowledge can build effective closed-loop design systems for sustainable proteins without needing major new data infrastructure or solving deep integration barriers.

What would settle it

A documented case in which an AI system designs a new sustainable protein formulation, accurately predicts its texture and taste from molecular inputs, and the predictions match results from physical lab tests and consumer trials with less total development time than traditional empirical methods.

read the original abstract

Global food systems must deliver nutritious, sustainable foods while sharply reducing environmental impact. Yet, food innovation remains slow, empirical, and fragmented. Artificial intelligence (AI) offers a transformative path to link molecular composition to functional performance, connect chemical structure to sensory outcomes, and accelerate cross-disciplinary innovation across the production pipeline. While broadly applicable to food systems, we focus on sustainable proteins--plant-based, fermentation-derived, and cultivated--as a high-impact testbed for AI-driven closed-loop design. We review the applications, opportunities, and challenges of AI for Food as an emerging discipline that integrates ingredient design, formulation development, fermentation and production, texture analysis, sensory science, manufacturing, and recipe generation. We identify four priorities: advancing scientific machine learning with embedded domain priors, treating food as a programmable biomaterial, building self-driving laboratories for automated discovery, and developing deep reasoning models that integrate nutrition and sustainability. Integrating AI responsibly into the food innovation cycle can accelerate the transition to sustainable food systems and establish a predictive, design-driven science of food for human and planetary health.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The manuscript is a perspective and review article arguing that AI can transform food innovation by linking molecular composition to functional performance and chemical structure to sensory outcomes. Focusing on sustainable proteins (plant-based, fermentation-derived, and cultivated) as a high-impact testbed, it reviews applications across ingredient design, formulation, production, texture, sensory science, manufacturing, and recipe generation, then identifies four priorities: advancing scientific machine learning with embedded domain priors, treating food as a programmable biomaterial, building self-driving laboratories for automated discovery, and developing deep reasoning models integrating nutrition and sustainability.

Significance. If the proposed integration of AI with food-science domain knowledge is realized, the work could help shift food innovation from empirical to predictive and design-driven approaches, accelerating sustainable protein development and broader food-system transitions. The manuscript synthesizes prior literature into a clear roadmap and gives credit to the potential of closed-loop systems, though it remains conceptual without new empirical results, proofs, or implementations.

major comments (1)
  1. [Abstract] Abstract and introduction: The central framing that existing AI techniques combined with domain priors can create effective closed-loop design systems for sustainable proteins without requiring major new data infrastructure is presented as feasible but lacks concrete references to current data limitations or successful pilot integrations in food systems; this assumption underpins the high-impact testbed claim and would benefit from explicit discussion of integration barriers.
minor comments (2)
  1. [Priorities section] The four priorities section would be strengthened by brief cross-references showing how scientific machine learning with domain priors differs from or supports the deep reasoning models priority.
  2. [Self-driving laboratories discussion] Add one or two specific citations to recent self-driving laboratory examples from chemistry or materials science when discussing automated discovery for food applications.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive feedback and recommendation for minor revision. We appreciate the opportunity to strengthen the manuscript's framing of closed-loop AI systems for sustainable proteins.

read point-by-point responses

  1. Referee: [Abstract] Abstract and introduction: The central framing that existing AI techniques combined with domain priors can create effective closed-loop design systems for sustainable proteins without requiring major new data infrastructure is presented as feasible but lacks concrete references to current data limitations or successful pilot integrations in food systems; this assumption underpins the high-impact testbed claim and would benefit from explicit discussion of integration barriers.

    Authors: We agree that an explicit discussion of data limitations and integration barriers would better support the central framing and the high-impact testbed claim. In the revised manuscript we will expand the introduction with a concise paragraph that (i) notes the current scarcity of large-scale, standardized, and interoperable datasets linking molecular composition to functional and sensory properties in food systems, (ii) acknowledges that major new data infrastructure is not assumed to be immediately available, and (iii) references early pilot integrations such as AI-assisted formulation platforms in plant-protein development and self-driving laboratory efforts in related fields. This addition will clarify the assumptions without changing the perspective nature of the work or requiring new empirical results. revision: yes

Circularity Check

0 steps flagged

Review paper with no mathematical derivations or self-referential predictions

full rationale

The manuscript is a review and perspective article that synthesizes external prior literature on AI applications in food innovation without presenting original empirical results, proofs, equations, or fitted models. No load-bearing steps reduce by construction to inputs, self-citations, or ansatzes; central claims are aspirational and rest on independent domain priors from food science and AI. This is the most common honest finding for such synthesis papers, scoring in the 0-2 range as self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

As a review paper the central framing rests on synthesis of prior literature in AI and food science rather than new postulates; no free parameters or invented entities are introduced.

axioms (1)
  • domain assumption Sustainable proteins serve as an effective high-impact testbed for AI-driven closed-loop design in food systems.
    Explicitly stated in the abstract as the chosen focus for the review.

pith-pipeline@v0.9.0 · 5781 in / 1143 out tokens · 42902 ms · 2026-05-18T13:32:34.178859+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models

    cs.CR 2026-04 conditional novelty 6.0

    A new benchmark exposes food-safety gaps in current LLMs and guardrails, and a fine-tuned 4B model is offered as a domain-specific fix.

  2. Generative AI for material design: A mechanics perspective from burgers to matter

    cs.CE 2026-04 unverdicted novelty 3.0

    Diffusion models from generative AI, sharing math with material mechanics, generate new burger recipes from 2,260 examples that some blind tasters prefer over the Big Mac.

Reference graph

Works this paper leans on

116 extracted references · 116 canonical work pages · cited by 2 Pith papers · 1 internal anchor

  1. [1]

    Diet for a Small Planet

    Lapp´ e, F.M. Diet for a Small Planet. Ballantine Books, New York (1971)

    work page 1971

  2. [2]

    A., et al

    Clark, M. A., et al. Global food system emissions could preclude achieving the 1.5 and 2C climate change targets.Science.370, 705-708 (2020)

    work page 2020

  3. [3]

    Xu, X. et al. Global greenhouse gas emissions from animal-based foods are twice those of plant- based foods.Nature Food.2, 724-732 (2021)

    work page 2021

  4. [4]

    Diet for a small footprint.Proc

    Keesing, F. Diet for a small footprint.Proc. Nat. Acad. Sci.119, e2204241119 (2022)

    work page 2022

  5. [5]

    Transforming a 12,000-year-old tech- nology.Nature Food3807-808 (2022)

    Friedrich, B. Transforming a 12,000-year-old tech- nology.Nature Food3807-808 (2022)

    work page 2022

  6. [6]

    Barabasi, A.L. et al. The unmapped chemical complexity of our diet.Nature Food133–37 (2020)

    work page 2020

  7. [7]

    Zeni, C. et al. A generative model for inorganic materials design.Nature.639624–632 (2025)

    work page 2025

  8. [8]

    Al-Sarayreh, M. et al. Inverse design and AI/Deep generative networks in food design: A comprehen- sive review.Trends Food Sci. Tech.138215–228 (2023)

    work page 2023

  9. [9]

    Datta, A. et al. Computer-aided food engineering. Nature Food.3894–904 (2022)

    work page 2022

  10. [10]

    Four ways to power-up ai for drug discovery.Nature, Feb

    King, A. Four ways to power-up AI for drug dis- covery.Nature.doi: 10.1038/d41586-025-00602-5 (2025)

    work page doi:10.1038/d41586-025-00602-5 2025

  11. [11]

    AI for food: accelerating and democra- tizing discovery and innovation.npj Sci

    Kuhl, E. AI for food: accelerating and democra- tizing discovery and innovation.npj Sci. Food.9, 82 (2025)

    work page 2025

  12. [12]

    Turing, A. M. Computing machinery and intelli- gence.Mind.LIX, 433-460 (1950)

    work page 1950

  13. [13]

    Rumelhart, D. E. et al. Learning representations by back-propagating errors.Nature.323, 533–536 (1986)

    work page 1986

  14. [14]

    Krizhevsky, A. et al. ImageNet classification with deep convolutional neural networks.Comm. ACM 60, 84–90 (2017)

    work page 2017

  15. [15]

    Goodfellow, I. et al. Generative adversarial networks. in:Advances in Neural Information Processing Systems (NeurIPS).27, 2672–2680 (2014)

    work page 2014

  16. [16]

    Vaswani, A. et al. Attention is all you need. in:Advances in Neural Information Processing Systems (NeurIPS).30, 5998–6008 (2017)

    work page 2017

  17. [17]

    Initial sequencing and analysis of the human genome..Nature409, 860–921 (2001)

    International Human Genome Sequencing Con- sortium. Initial sequencing and analysis of the human genome..Nature409, 860–921 (2001)

    work page 2001

  18. [18]

    Gilmer, J. et al. Neural message passing for quan- tum chemistry. in:Proc. 34th Int. Conf. Machine Learning (ICML).34, 1263–1272 (2017)

    work page 2017

  19. [19]

    Zeevi, D. et al. Personalized nutrition by predic- tion of glycemic responses.Cell163, 1079–1094 (2015)

    work page 2015

  20. [20]

    Gordon, E. B. et al. Biomaterials in cellular agri- culture and plant-based foods for the future.Nat. Rev. Materials10, 500-518 (2025)

    work page 2025

  21. [21]

    Schreurs, M. et al. Predicting and improving com- plex beer flavor through machine learning.Nat. Comm.15, 2368 (2024)

    work page 2024

  22. [22]

    Lee, B.-K. et al. A principal odor map unifies diverse tasks in olfactory perception.Science. 381, 999-1006 (2023)

    work page 2023

  23. [23]

    Jumper, J. et al. Highly accurate protein struc- ture prediction with AlphaFold.Nature.596, 583–589 (2021)

    work page 2021

  24. [24]

    Butler, K. T. et al. Machine learning for molec- ular and materials science.Nature.559, 547–555 (2018). 14

    work page 2018

  25. [25]

    Graham, A. E. & Ledesma-Amaro, R. The micro- bial food revolution.Nat. Comm.14, 2231 (2023)

    work page 2023

  26. [26]

    Alternative protein sources: science-powered startups to fuel food innovation

    Lurie-Luke, E. Alternative protein sources: science-powered startups to fuel food innovation. Nat. Comm.15, 4425 (2024)

    work page 2024

  27. [27]

    Kyriakopoulou, K. et al. Plant-based meat ana- logues. in:Sustainable Meat Production and Pro- cessing, Academic Press, 103–126 (2019)

    work page 2019

  28. [28]

    Loveday, S. M. Food proteins: Technological, nutritional, and sustainability attributes of tradi- tional and emerging proteins.Ann. Rev. Food Sci. Tech.10, 311–339 (2019)

    work page 2019

  29. [29]

    & Xiong, Y

    Sha, L. & Xiong, Y. L. Plant protein-based alternatives of reconstructed meat: Science, tech- nology, and challenges.Trends Food Sci. & Tech. 102, 51–61 (2020)

    work page 2020

  30. [30]

    Proteins from land plants—Potential resources for human nutrition and food security

    Day, L. Proteins from land plants—Potential resources for human nutrition and food security. Trends Food Sci. & Tech.32, 25–42 (2013)

    work page 2013

  31. [31]

    Fasolin, L. H.. et al. Emergent food pro- teins—Towards sustainability, health and innova- tion.Foods.10, 600 (2021)

    work page 2021

  32. [32]

    Haque, M. A.. et al. Food proteins, structure, and function. in:Reference Module in Food Science., Elsevier (2016)

    work page 2016

  33. [33]

    McClements, D. J. Development of next- generation nutritionally fortified plant-based milk substitutes: Structural design principles.Foods.9, 421 (2020)

    work page 2020

  34. [34]

    Lie-Piang, A. et al. Quantifying techno-functional properties of ingredients from multiple crops using machine learning.Curr. Res. Food Sci.7, 100601 (2023)

    work page 2023

  35. [35]

    Siddiqui, H. et al. A review of the health benefits, functional properties, and ultrasound- assisted dietary fiber extraction.Bioact. Carbo- hyd. Diet. Fibre.30, 100356 (2023)

    work page 2023

  36. [36]

    Colloids in food: Ingredients, struc- ture, and stability.Ann

    Dickinson, E. Colloids in food: Ingredients, struc- ture, and stability.Ann. Rev. Food Sci. Tech.6, 211–233 (2015)

    work page 2015

  37. [37]

    Liu, M.-Q. et al. Digging natural emulsifiers based on machine learning and exploration their per- formance for stabilizing dairy products.SSRN. https://ssrn.com/abstract=4994781 (2025)

    work page 2025

  38. [38]

    Siejak, P. et al. The prediction of pectin vis- cosity using machine learning based on physical characteristics—case study: Aglupectin HS-MR. Sustainability.16, 5877 (2024)

    work page 2024

  39. [39]

    Kraessig, P. M. et al. Sensory-biased autoencoder enables prediction of texture perception from food rheology.Food Res. Int.205, 116007 (2025)

    work page 2025

  40. [40]

    Meng, Y. et al. Advancing salt reduction tech- nologies: AI-assisted structural design of starch- based emulsion gel systems for next-generation low sodium food formulations.Trends Food Sci. & Tech.doi:10.1016/j.tifs.2025.105234 (2025)

    work page doi:10.1016/j.tifs.2025.105234 2025

  41. [41]

    Yilmaz, M. T. et al. Explainable AI-driven eval- uation of plant protein rheology using tree-based and Gaussian process machine learning models. Ain Shams Eng. J.16, 103565 (2025)

    work page 2025

  42. [42]

    Latent space method of generating food formulas.US 10,915,818.Feb 9, 2021

    NotCo. Latent space method of generating food formulas.US 10,915,818.Feb 9, 2021

    work page 2021

  43. [43]

    Neural network method of generating food formulas.US 10,957,424.Mar 23, 2021

    NotCo. Neural network method of generating food formulas.US 10,957,424.Mar 23, 2021

    work page 2021

  44. [44]

    Systems and methods to mimic tar- get food items using artificial intelligence.US 11,164,478.Nov 2, 2021

    NotCo. Systems and methods to mimic tar- get food items using artificial intelligence.US 11,164,478.Nov 2, 2021

    work page 2021

  45. [45]

    Controllable formula generation.US 11,164,069.Nov 2, 2021

    NotCo. Controllable formula generation.US 11,164,069.Nov 2, 2021

    work page 2021

  46. [46]

    Martin, J. et al. Recipe1M+: A dataset for learn- ing cross-modal embeddings for cooking recipes and food images.IEEE Trans. Pattern Anal. Mach. Intell.43(2021)

    work page 2021

  47. [47]

    Park, D. et al. FlavorGraph: a large-scale food- chemical graph for generating food representa- tions and recommending food pairings.Sci. Rep. 11, 931 (2021)

    work page 2021

  48. [48]

    Garg, N. et al. FlavorDB: a database of flavor molecules.Nucl. Acids Res.46, D1210–D1216 (2018)

    work page 2018

  49. [49]

    Ahn, Y.-Y. et al. Flavor network and the princi- ples of food pairing.Sci. Rep.1, 196 (2011)

    work page 2011

  50. [50]

    Feng, X. et al. Enhanced lipid production by Chlorella pyrenoidosa through magnetic field pretreatment of wastewater and treatment of microalgae-wastewater culture solution: Magnetic field treatment modes and conditions.Bioresour. Technol.206, 123102 (2020)

    work page 2020

  51. [51]

    Sharma, D. et al. Response surface methodol- ogy and artificial neural network modelling for enhancing maturity parameters during vermicom- posting of floral waste.Bioresour. Technol.324, 124672 (2021)

    work page 2021

  52. [52]

    Liao X. et al. Artificial Intelligence: A solution to involution of Design-Build-Test-Learn cycleCurr. Op. Biotechnol.75, 102712 (2022). 15

    work page 2022

  53. [53]

    Liu, L. et al. Modeling and optimization of micro- bial hyaluronic acid production by Streptococcus zooepidemicus using radial basis function neu- ral network coupling quantum-behaved particle swarm optimization algorithm.Biotechnol. Prog. 25, 1819–1825 (2009)

    work page 2009

  54. [54]

    Jia, R. et al. Exploration of deep learning models for real-time monitoring of state and perfor- mance of anaerobic digestion with online sensors. Bioresour. Technol.363, 127908 (2022)

    work page 2022

  55. [55]

    Rathore, A. S. et al. Bioprocess control: Current progress and future perspectivesLife.11, 557 (2025)

    work page 2025

  56. [56]

    Reardon, K. F. Practical monitoring technolo- gies for cells and substrates in biomanufacturing. Curr. Opin. Biotechnol.71, 225–230 (2021)

    work page 2021

  57. [57]

    Cheng, Y. et al. Artificial intelligence technolo- gies in bioprocess: Opportunities and challenges. Biores. Tech.369,128451 (2023)

    work page 2023

  58. [58]

    Treloar, N.J. et al. Deep reinforcement learn- ing for the control of microbial co-cultures in bioreactors.PLoS Comput. Biol.16, e1007783 (2020)

    work page 2020

  59. [59]

    Singhal, A. et al. Pretreatment of Leucaena leuco- cephala wood by acidified glycerol: optimization, severity index and correlation analysis.Bioresour. Technol.265, 214–223 (2018)

    work page 2018

  60. [60]

    Austerjost, J. et al. A machine vision approach for bioreactor foam sensing.SLAS. Technol.26, 408–414 (2021)

    work page 2021

  61. [61]

    Butean, A. et al. A review of artificial intelli- gence applications for biorefineries and biopro- cessing: From data-driven processes to optimiza- tion strategies and real-time control.Processes. 13, 2544 (2025)

    work page 2025

  62. [62]

    Alejo, L. et al. Effluent composition prediction of a two-stage anaerobic digestion process: machine learning and stoichiometry techniques.Environ. Sci. Pollut. Res. Int.25, 21149–21163 (2018)

    work page 2018

  63. [63]

    Akinade, O. O. & Oyedele, L. O. Integrating construction supply chains within a circular econ- omy: An ANFIS-based waste analytics system (A-WAS).J. Clean. Prod.229, 863–873 (2019)

    work page 2019

  64. [64]

    Peng, J. et al. Time-dependent fermentation con- trol strategies for enhancing synthesis of marine bacteriocin 1701 using artificial neural network and genetic algorithm.Bioresour. Technol.138, 345–352 (2013)

    work page 2013

  65. [65]

    & Singh, K

    Sharma, D. & Singh, K. AI-enhanced bioprocess technologies: machine learning implementations from upstream to downstream operations.World J. Microbio. Biotech.41, 278 (2025)

    work page 2025

  66. [66]

    Holzinger A. et al. AI for Life: Trends in Artificial Intelligence for biotechnology.New Biotech.16-24 (2023)

    work page 2023

  67. [67]

    & Buehler, M

    Ghafarollahi, A. & Buehler, M. J. ProtA- gents: protein discovery via large language model multi-agent collaborations combining physics and machine learning.Digit. Discovery..3, 1389-1409 (2024)

    work page 2024

  68. [68]

    Pierre, S

    St. Pierre, S. R. et al. Discovering the mechan- ics of artificial and real meat.Comp. Meth. Appl. Mech. Eng.415, 116236 (2023)

    work page 2023

  69. [69]

    Pierre, S

    St. Pierre, S. R. et al. The mechanical and sen- sory signature of plant-based and animal meat. npj Sci. Food.8, 94 (2024)

    work page 2024

  70. [70]

    Sanahuja, M. et al. Classification of puffed snacks freshness based on crispiness-related mechani- cal and acoustical properties.J. Food Eng.226, 53–64 (2018)

    work page 2018

  71. [71]

    Dahl, J. F. et al. Predicting rheological parame- ters of food biopolymer mixtures using machine learning.Food Hydrocoll.160, 110786 (2025)

    work page 2025

  72. [72]

    Zhang, Y. et al. Construction of an intelligent recognition system for the cooking doneness of deep-fried golden pompano (Trachinotus ovatus) based on deep learning.Food Biosci.68, 106644 (2025)

    work page 2025

  73. [73]

    Saalbrink, J. et al. Quantifying microscopic droplets in colloidal systems through machine learning-based image analysis.Food Hydrocoll. 166, 111301 (2025)

    work page 2025

  74. [74]

    Dunne, R. A. et al. Texture profile analysis and rheology of plant-based and animal meat.Food Res. Int.205, 115876 (2025)

    work page 2025

  75. [75]

    Munekata, P. E. S. et al. Applications of elec- tronic nose, electronic eye and electronic tongue in quality, safety and shelf life of meat and meat products: A review.Sensors.23, 672 (2023)

    work page 2023

  76. [76]

    Karakaya, D. et al. Electronic nose and its applications: A survey.Int. J. Auto. Comp.17, 179–209 (2019)

    work page 2019

  77. [77]

    Bengio, Y. et al. Representation learning: A review and new perspectives.IEEE Trans. Pat- tern Anal. Machine Intell.35, 1798-1828 (2012)

    work page 2012

  78. [78]

    Feng, D. et al. SMELLNET: A large-scale dataset for real-world smell recognition.arXiv doi:10.48550/arXiv.2506.00239 (2025). 16

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2506.00239 2025

  79. [79]

    Tom, G. et al. From molecules to mix- tures: Learning representations of olfactory mix- ture similarity using inductive biases.arXiv doi:10.48550/arXiv.2501.16271 (2025)

    work page doi:10.48550/arxiv.2501.16271 2025

  80. [80]

    Istif, E. et al. Miniaturized wireless sensor enables real-time monitoring of food spoilage.Nature Food.4, 427–436 (2023)

    work page 2023

Showing first 80 references.