{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T23:46:00Z","timestamp":1775691960621,"version":"3.50.1"},"posted":{"date-parts":[[2026]]},"group-title":"SSRN","reference-count":38,"publisher":"Elsevier BV","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Predicting the perceived intensity of odorants remains a fundamental challenge in sensory science due to the complex, non-linear behavior of their response, as well as the difficulty in correlating molecular structure with human perception. While traditional deep learning models, such as Graph Convolutional Networks (GCNs), excel at capturing molecular topology, they often fail to account for the biological and perceptual context of olfaction. This study introduces VIANA, a novel \"tri-pillar\" framework that integrates structural graph theory, character value embeddings, and phenomenological behavior. This methodology systematically evaluates knowledge transfer across three distinct domains: molecular structure via GCNs, semantic odor character values via Principal Odor Map (POM) embeddings, and biological dose-response logic via Hill\u2019s law. We demonstrate that knowledge transfer is not inherently positive; rather, a balance must be maintained in the volume of information provided to the model. While raw semantic data led to \"information overload\" in domain-informed models, applying Principal Component Analysis (PCA) to distill the 95% most impactful semantic variance yielded a superior \"signal distillation\" effect. Results indicate that the synthesis of these three knowledge transfer pillars significantly outperforms baseline structural models, with VIANA achieving a peak R^2\u00a0of 0.996 and a test Mean Squared Error (MSE) of 0.19. In this context, VIANA successfully captures the physical ceiling of saturation, the sensitivity of detection thresholds, and the nuance of odor character value expression, providing a domain-grounded simulation of the human olfactory experience. This research provides a robust framework for digital olfaction, effectively bridging the gap between molecular informatics and sensory perception.<\/jats:p>","DOI":"10.2139\/ssrn.6545771","type":"posted-content","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T22:39:24Z","timestamp":1775687964000},"source":"Crossref","is-referenced-by-count":0,"title":["VIANA: character Value-enhanced Intensity Assessment via domain-informed Neural Architectur"],"prefix":"10.2139","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3092-8136","authenticated-orcid":true,"given":"Luana","family":"Queiroz","sequence":"first","affiliation":[]},{"given":"\u00cdcaro","family":"Bernardes","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4269-1420","authenticated-orcid":true,"given":"Ana  M.","family":"Ribeiro","sequence":"additional","affiliation":[]},{"given":"Bernardo","family":"Aguilera-Mercado","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0963-6449","authenticated-orcid":true,"given":"Idelfonso  B. R.","family":"Nogueira","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"ref1","author":"Statista","year":"2026","journal-title":"Fragrances -worldwide | statista market forecast"},{"issue":"3","key":"ref2","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1111\/j.1469-185X.2007.00019.x","article-title":"The sense of smell: molecular basis of odorant recognition","volume":"82","author":"Manuel Zarzo","year":"2007","journal-title":"Biological Reviews"},{"issue":"8","key":"ref3","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/j.tins.2014.05.005","article-title":"From molecule to mind: an integrative perspective on odor intensity","volume":"37","author":"Johan N Joel D Mainland","year":"2014","journal-title":"Trends in neurosciences"},{"issue":"33","key":"ref4","doi-asserted-by":"crossref","first-page":"14480","DOI":"10.1021\/acs.iecr.4c00650","article-title":"Molecule generation and optimization for efficient fragrance creation","volume":"63","author":"Bruno Cl Rodrigues","year":"2024","journal-title":"Industrial & Engineering Chemistry Research"},{"key":"ref5","author":"Vinicius Santana","year":"2023","journal-title":"Ana Mafalda Ribeiro, Chris Rackauckas, and Idelfonso Nogueira. Advancing odor classification models enhanced by scientific machine learning and mechanistic model: Probabilistic weight assignment for odor intensity prediction and uncertainty analysis for robust fragrance classification"},{"key":"ref6","first-page":"1","article-title":"Machine learning approaches for gc-ms data interpretation in flavour and fragrance analysis","author":"Jean-Baptiste Coffin","journal-title":"Flavour and Fragrance Journal"},{"issue":"20","key":"ref7","article-title":"An nlp-based perfume note estimation based on descriptive sentences","volume":"14","author":"Jooyoung Kim","year":"2024","journal-title":"Applied Sciences"},{"key":"ref8","author":"Peter Fichtelmann","year":"2025","journal-title":"Machine learning for smell: Ordinal odor strength prediction of molecular perfumery components"},{"key":"ref9","article-title":"On the prediction of critical heat flux using a physics-informed machine learning-aided framework","volume":"164","author":"Xingang Zhao","year":"2020","journal-title":"Applied Thermal Engineering"},{"issue":"18","key":"ref10","doi-asserted-by":"crossref","first-page":"7833","DOI":"10.1021\/acs.chemmater.7b02532","article-title":"Predicting the mechanical properties of zeolite frameworks by machine learning","volume":"29","author":"D Jack","year":"2017","journal-title":"Chemistry of Materials"},{"key":"ref11","article-title":"Puffin: A path-unifying feedforward interfaced network for vapor pressure prediction","volume":"286","author":"Viena Vinicius","year":"2024","journal-title":"Chemical Engineering Science"},{"key":"ref12","author":"Carine Menezes Rebello","year":"2025","journal-title":"Expuffin: Thermodynamic consistent viscosity prediction in an extended path-unifying feed-forward interfaced network"},{"key":"ref13","article-title":"Hybridgamma: A thermodynamically consistent framework for hybrid modelling of activity coefficients","volume":"475","author":"Ulderico Di Caprio","year":"2023","journal-title":"Chemical Engineering Journal"},{"key":"ref14","article-title":"Complementary codes for odor identity and intensity in olfactory cortex","volume":"6","author":"Kevin A Bolding","year":"2017","journal-title":"Elife"},{"issue":"1","key":"ref15","article-title":"Olfactory perception of chemically diverse molecules","volume":"17","author":"Andreas Keller","year":"2016","journal-title":"BMC neuroscience"},{"issue":"8","key":"ref16","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1093\/chemse\/bji057","article-title":"Color enhances orthonasal olfactory intensity and reduces retronasal olfactory intensity","volume":"30","author":"Brian J Koza","year":"2005","journal-title":"Chemical senses"},{"issue":"15","key":"ref17","doi-asserted-by":"crossref","first-page":"6285","DOI":"10.1523\/JNEUROSCI.0426-12.2013","article-title":"Intensity invariant dynamics and odor-specific latencies in olfactory receptor neuron response","volume":"33","author":"Carlotta Martelli","year":"2013","journal-title":"Journal of Neuroscience"},{"issue":"3","key":"ref18","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1152\/jn.1986.56.3.572","article-title":"Patterned response to odor in mammalian olfactory bulb: the influence of intensity","volume":"56","author":"Michael Meredith","year":"1986","journal-title":"Journal of neurophysiology"},{"issue":"4","key":"ref19","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1111\/j.1745-459X.2004.tb00150.x","article-title":"Evaluation of olfactory intensity: Comparative study of two methods","volume":"19","author":"Boriana Atanasova","year":"2004","journal-title":"Journal of Sensory Studies"},{"issue":"10","key":"ref20","article-title":"A framework for predicting odor threshold values of perfumes by scientific machine learning and transfer learning","volume":"9","author":"Luis Mc Oliveira","journal-title":"Heliyon"},{"issue":"32","key":"ref21","doi-asserted-by":"crossref","first-page":"15036","DOI":"10.1021\/acs.iecr.9b01225","article-title":"Method for predicting odor intensity of perfumery raw materials using dose-response curve database","volume":"58","author":"Hideki Wakayama","year":"2019","journal-title":"Industrial & Engineering Chemistry Research"},{"key":"ref22","volume":"2","author":"Roman Yevgeniy B Sirotin","year":"2015","journal-title":"Neural coding of perceived odor intensity"},{"issue":"1","key":"ref23","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1021\/acs.jcim.3c01250","article-title":"Chemprop: a machine learning package for chemical property prediction","volume":"64","author":"Esther Heid","year":"2023","journal-title":"Journal of chemical information and modeling"},{"issue":"6661","key":"ref24","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1126\/science.ade4401","article-title":"A principal odor map unifies diverse tasks in olfactory perception","volume":"381","author":"Brian K Lee","year":"2023","journal-title":"Science"},{"issue":"6","key":"ref25","article-title":"Gender difference in ratings of odor intensity during olfactory training","volume":"37","author":"Yun-Ting Chao","year":"2022","journal-title":"Journal of Sensory Studies"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1520\/DS61-EB","author":"Andrew Dravnieks","year":"1992","journal-title":"Atlas of odor character profiles"},{"key":"ref27","first-page":"991","volume":"39","author":"Mark Stopfer","year":"2003","journal-title":"tensity versus identity coding in an olfactory system. Neuron"},{"issue":"22","key":"ref28","doi-asserted-by":"crossref","first-page":"11999","DOI":"10.1021\/acs.analchem.7b02389","article-title":"Machine-learning-based olfactometer: prediction of odor perception from physicochemical features of odorant molecules","volume":"89","author":"Liang Shang","year":"2017","journal-title":"Analytical chemistry"},{"issue":"2","key":"ref29","article-title":"Accurate prediction of personalized olfactory perception from large-scale chemoinformatic features","volume":"7","author":"Hongyang Li","year":"2018","journal-title":"Gigascience"},{"issue":"6327","key":"ref30","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1126\/science.aal2014","article-title":"Predicting human olfactory perception from chemical features of odor molecules","volume":"355","author":"Andreas Keller","year":"2017","journal-title":"Science"},{"key":"ref31","article-title":"Optuna: A next-generation hyperparameter optimization framework","author":"Takuya Akiba","year":"2019","journal-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"},{"issue":"1","key":"ref32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40649-019-0069-y","article-title":"Graph convolutional networks: a comprehensive review","volume":"6","author":"Si Zhang","year":"2019","journal-title":"Computational Social Networks"},{"key":"ref33","article-title":"Graph-based deep learning techniques for remote sensing applications: Techniques, taxonomy, and applications-a comprehensive review","volume":"50","author":"Khazri Manel","year":"2023","journal-title":"Computer Science Review"},{"key":"ref34","author":"Matthias Fey","year":"2026","journal-title":"Pytorch geometric documentation"},{"key":"ref35","author":"Matt Swain","year":"2026","journal-title":"Pubchempy documentation"},{"key":"ref36","first-page":"8024","article-title":"Pytorch: An imperative style, highperformance deep learning library","volume":"32","author":"Adam","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","author":"Greg Landrum","year":"2026","journal-title":"The rdkit cookbook"},{"issue":"3","key":"ref38","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/0098-3004(93)90090-R","article-title":"Principal components analysis (pca)","volume":"19","author":"Andrzej Ma?kiewicz","year":"1993","journal-title":"Computers Geosciences"}],"container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T22:47:56Z","timestamp":1775688476000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ssrn.com\/abstract=6545771"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":38,"URL":"https:\/\/doi.org\/10.2139\/ssrn.6545771","relation":{},"subject":[],"published":{"date-parts":[[2026]]},"subtype":"preprint"}}