EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Learning structured population models from data with WSINDy

Rainey Lyons iD, Vanja Dukic, David M Bortz

PLOS Computational Biology · 08.12.2025 · 21 (12) · e1013742

DOI: 10.1371/journal.pcbi.1013742 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 08.12.2025. Verfasst von Rainey Lyons und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Applied Mathematics, University of Colorado, Boulder, Colorado, United States of America. Hauptthemen laut MEDLINE: Machine Learning, Population Dynamics, Nonlinear Dynamics, Models, Biological. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, NIGMS Division of Biophysics, Biomedical Technology and Computational Biosciences, Division of Molecular and Cellular Biosciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Characteristics of individuals in a population, such as age and size, play a key role in determining how populations change over time. In contexts of population dynamics, identifying effective model features, such as fecundity and mortality rates, is generally a complex and computationally intensive process, especially when the dynamics are heterogeneous across the population. In this work, we propose a Weak form Scientific Machine Learning-based method for selecting appropriate model ingredients from a library of scientifically feasible functions used to model structured populations. This paper presents extensions of the Weak form Sparse Identification of Nonlinear Dynamics (WSINDy) method to select the best-fitting ingredients from noisy time-series histogram data. This extension includes learning heterogeneous dynamics and also learning the boundary processes (such as birth) of the model directly from the data. We additionally incorporate a cross-validation method which helps fine tune the recovered boundary process hyperparameters to the data. Several test cases are considered, demonstrating the method’s performance for several standard models from population modeling, including age and size-structured models. Through these examples, we examine both the advantages and limitations of the method, with a particular focus on the distinguishability of terms in the library.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningPopulation DynamicsNonlinear DynamicsModels, BiologicalHumansComputational BiologyAlgorithmsComputer Simulation

Autor:innen und Institutionen

  • Department of Applied Mathematics, University of Colorado, Boulder, Colorado, United States of America.

ORCID-Profile: Rainey Lyons

Förderung

  • NIGMS NIH HHS
  • NIGMS Division of Biophysics, Biomedical Technology and Computational Biosciences
  • Division of Molecular and Cellular Biosciences
  • NSF Division Of Environmental Biology
  • NIFA Biological Sciences

Zitieren

APA

Lyons, R., Dukic, V., & Bortz, D. M. (2025). Learning structured population models from data with WSINDy. PLOS Computational Biology, 21(12), e1013742. https://doi.org/10.1371/journal.pcbi.1013742

Vancouver

Lyons R, Dukic V, Bortz DM. Learning structured population models from data with WSINDy. PLOS Computational Biology. 2025;21(12):e1013742. doi:10.1371/journal.pcbi.1013742

BibTeX
@article{Lyons2025,
  author = {Lyons, Rainey and Dukic, Vanja and Bortz, David M},
  title = {Learning structured population models from data with WSINDy},
  journal = {PLOS Computational Biology},
  year = {2025},
  volume = {21},
  number = {12},
  pages = {e1013742},
  doi = {10.1371/journal.pcbi.1013742}
}
Kostenlos starten →