Adapting physics-informed neural networks to improve ODE optimization in mosquito population dynamics.
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...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2024-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0315762 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841555458128609280 |
|---|---|
| author | Dinh Viet Cuong Branislava Lalić Mina Petrić Nguyen Thanh Binh Mark Roantree |
| author_facet | Dinh Viet Cuong Branislava Lalić Mina Petrić Nguyen Thanh Binh Mark Roantree |
| author_sort | Dinh Viet Cuong |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-5bc0129a51d84857806db47443348427 |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-5bc0129a51d84857806db474433484272025-01-08T05:32:40ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-011912e031576210.1371/journal.pone.0315762Adapting physics-informed neural networks to improve ODE optimization in mosquito population dynamics.Dinh Viet CuongBranislava LalićMina PetrićNguyen Thanh BinhMark RoantreePhysics 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.https://doi.org/10.1371/journal.pone.0315762 |
| spellingShingle | Dinh Viet Cuong Branislava Lalić Mina Petrić Nguyen Thanh Binh Mark Roantree Adapting physics-informed neural networks to improve ODE optimization in mosquito population dynamics. PLoS ONE |
| title | Adapting physics-informed neural networks to improve ODE optimization in mosquito population dynamics. |
| title_full | Adapting physics-informed neural networks to improve ODE optimization in mosquito population dynamics. |
| title_fullStr | Adapting physics-informed neural networks to improve ODE optimization in mosquito population dynamics. |
| title_full_unstemmed | Adapting physics-informed neural networks to improve ODE optimization in mosquito population dynamics. |
| title_short | Adapting physics-informed neural networks to improve ODE optimization in mosquito population dynamics. |
| title_sort | adapting physics informed neural networks to improve ode optimization in mosquito population dynamics |
| url | https://doi.org/10.1371/journal.pone.0315762 |
| work_keys_str_mv | AT dinhvietcuong adaptingphysicsinformedneuralnetworkstoimproveodeoptimizationinmosquitopopulationdynamics AT branislavalalic adaptingphysicsinformedneuralnetworkstoimproveodeoptimizationinmosquitopopulationdynamics AT minapetric adaptingphysicsinformedneuralnetworkstoimproveodeoptimizationinmosquitopopulationdynamics AT nguyenthanhbinh adaptingphysicsinformedneuralnetworkstoimproveodeoptimizationinmosquitopopulationdynamics AT markroantree adaptingphysicsinformedneuralnetworkstoimproveodeoptimizationinmosquitopopulationdynamics |