EUVIMEDEUVIMED entdecken
Crossref

Sensitivity Analysis on a Computational Model of Olfaction Using Gaussian Process, Generalized Polynomial Chaos and Neural Networks

Vidya Chandrasekaran, Yanyan He, Dominick Ohara, Lindsay Waldrop

Bulletin of Mathematical Biology · 2026

DOI: 10.1007/s11538-026-01768-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bulletin of Mathematical Biology, 2026. Verfasst von Vidya Chandrasekaran und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics, University of North Texas, 1155 Union Circle, Denton, TX, 76203, USA. Hauptthemen laut MEDLINE: Smell, Models, Biological. Die Arbeit nennt 52 Literaturangaben. Gefördert von: Army Research Office.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The process of odor capture by arrays of chemosensory hairs is a complex phenomenon influenced by multiple factors, such as hair morphology and surrounding fluid characteristics. Understanding how these parameters affect the fluid flow and odor transport is critical for advancing biological understanding and informing the potential design of bio-inspired sensing systems. However, performing comprehensive analyses with high-fidelity computational fluid dynamics models can be computationally expensive. To address this challenge, we investigate three surrogate modeling approaches - Gaussian process regression, generalized polynomial chaos and feedforward neural networks - as efficient numerical approximations to full simulations. These surrogates are trained on a limited number of simulations and then used to predict system responses efficiently. Their predictive accuracy is compared using synthetic examples across a range of scenarios. For the biological application considered here, cross-validation is employed to identify the surrogate model with the best performance. Using these surrogate models, we implement a variance-based global sensitivity analysis method to analyze the impact of uncertainty of inputs (such as morphological variables) on flow characteristics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SmellModels, BiologicalComputer SimulationNormal DistributionNeural Networks, ComputerFeedforward Neural NetworksNonlinear DynamicsMathematical ConceptsHydrodynamicsAnimalsHumansOdorantsComputational BiologySoft Computing

Stichwörter der Autor:innen

Fluid dynamicsGaussian processGeneralized polynomial chaosNeural networksOlfactionSensitivity analysis

Autor:innen und Institutionen

  • Department of Mathematics, University of North Texas, 1155 Union Circle, Denton, TX, 76203, USA.
  • Department of Mathematics, and Department of Computer Science and Engineering, University of North Texas, 1155 Union Circle, Denton, TX, 76203, USA. yanyan.he@unt.edu.
  • Schmid College of Science and Technology, Chapman University, One University Drive, Orange, CA, 92866, USA.

Förderung

  • Army Research Office

Zitieren

APA

Chandrasekaran, V., He, Y., Ohara, D., & Waldrop, L. (2026). Sensitivity Analysis on a Computational Model of Olfaction Using Gaussian Process, Generalized Polynomial Chaos and Neural Networks. Bulletin of Mathematical Biology. https://doi.org/10.1007/s11538-026-01768-3

Vancouver

Chandrasekaran V, He Y, Ohara D, Waldrop L. Sensitivity Analysis on a Computational Model of Olfaction Using Gaussian Process, Generalized Polynomial Chaos and Neural Networks. Bulletin of Mathematical Biology. 2026. doi:10.1007/s11538-026-01768-3

BibTeX
@article{Chandrasekaran2026,
  author = {Chandrasekaran, Vidya and He, Yanyan and Ohara, Dominick and Waldrop, Lindsay},
  title = {Sensitivity Analysis on a Computational Model of Olfaction Using Gaussian Process, Generalized Polynomial Chaos and Neural Networks},
  journal = {Bulletin of Mathematical Biology},
  year = {2026},
  doi = {10.1007/s11538-026-01768-3}
}
Kostenlos starten →