Adapting physics-informed neural networks to improve ODE optimization in mosquito population dynamics
PLOS ONE · 23.12.2024 · 19 (12) · e0315762
DOI: 10.1371/journal.pone.0315762 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 23.12.2024. Verfasst von Dinh Viet Cuong und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computing, Dublin City University, Dublin, Ireland. Hauptthemen laut MEDLINE: Neural Networks, Computer, Population Dynamics, Culicidae. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 84 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science Foundation Ireland, European Cooperation in Science and Technology.
Abstract (Originalsprache)
Physics informed neural networks have been gaining popularity due to their unique ability to incorporate physics laws into data-driven models, ensuring that the predictions are not only consistent with empirical data but also align with domain-specific knowledge in the form of physics equations. The integration of physics principles enables the method to require less data while maintaining the robustness of deep learning in modelling complex dynamical systems. However, current PINN frameworks are not sufficiently mature for real-world ODE systems, especially those with extreme multi-scale behavior such as mosquito population dynamical modelling. In this research, we propose a PINN framework with several improvements for forward and inverse problems for ODE systems with a case study application in modelling the dynamics of mosquito populations. The framework tackles the gradient imbalance and stiff problems posed by mosquito ordinary differential equations. The method offers a simple but effective way to resolve the time causality issue in PINNs by gradually expanding the training time domain until it covers entire domain of interest. As part of a robust evaluation, we conduct experiments using simulated data to evaluate the effectiveness of the approach. Preliminary results indicate that physics-informed machine learning holds significant potential for advancing the study of ecological systems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Computing, Dublin City University, Dublin, Ireland.
- Faculty of Agriculture, University of Novi Sad, Novi Sad, Serbia.
- Avia-GIS NV, Zoersel, Belgium.
- University of Science, Ho Chi Minh City, Vietnam.
- Insight Centre for Data Analytics, Dublin City University, Dublin, Ireland.
ORCID-Profile: Dinh Viet Cuong, Mark Roantree
Förderung
- Science Foundation Ireland
- European Cooperation in Science and Technology
Zitieren
APA
Viet Cuong, D., Lalić, B., Petrić, M., Thanh Binh, N., & Roantree, M. (2024). Adapting physics-informed neural networks to improve ODE optimization in mosquito population dynamics. PLOS ONE, 19(12), e0315762. https://doi.org/10.1371/journal.pone.0315762
Vancouver
Viet Cuong D, Lalić B, Petrić M, Thanh Binh N, Roantree M. Adapting physics-informed neural networks to improve ODE optimization in mosquito population dynamics. PLOS ONE. 2024;19(12):e0315762. doi:10.1371/journal.pone.0315762
BibTeX
@article{VietCuong2024,
author = {Viet Cuong, Dinh and Lalić, Branislava and Petrić, Mina and Thanh Binh, Nguyen and Roantree, Mark},
title = {Adapting physics-informed neural networks to improve ODE optimization in mosquito population dynamics},
journal = {PLOS ONE},
year = {2024},
volume = {19},
number = {12},
pages = {e0315762},
doi = {10.1371/journal.pone.0315762}
}
EUVIMED