Physics-Informed Neural Networks Integrating Compartmental Model for Analyzing COVID-19 Transmission Dynamics
Modelling and predicting the behaviour of infectious diseases is essential for early warning and evaluating the most effective interventions to prevent significant harm. Compartmental models produce a system of ordinary differential equations (ODEs) that are renowned for simulating the transmission...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Viruses |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4915/15/8/1749 |
| _version_ | 1797583034502873088 |
|---|---|
| author | Xiao Ning Jinxing Guan Xi-An Li Yongyue Wei Feng Chen |
| author_facet | Xiao Ning Jinxing Guan Xi-An Li Yongyue Wei Feng Chen |
| author_sort | Xiao Ning |
| collection | DOAJ |
| description | Modelling and predicting the behaviour of infectious diseases is essential for early warning and evaluating the most effective interventions to prevent significant harm. Compartmental models produce a system of ordinary differential equations (ODEs) that are renowned for simulating the transmission dynamics of infectious diseases. However, the parameters in compartmental models are often unknown, and they can even change over time in the real world, making them difficult to determine. This study proposes an advanced artificial intelligence approach based on physics-informed neural networks (PINNs) to estimate time-varying parameters from given data for the compartmental model. Our proposed PINNs method captures the complex dynamics of COVID-19 by integrating a modified Susceptible-Exposed-Infectious-Recovered-Death (SEIRD) compartmental model with deep neural networks. Specifically, we modelled the system of ODEs as one network and the time-varying parameters as another network to address significant unknown parameters and limited data. Such structure of the PINNs method is in line with the prior epidemiological correlations and comprises the mismatch between available data and network output and the residual of ODEs. The experimental findings on real-world reported data data have demonstrated that our method robustly and accurately learns the dynamics and forecasts future states. Moreover, as more data becomes available, our proposed PINNs method can be successfully extended to other regions and infectious diseases. |
| first_indexed | 2024-03-10T23:31:07Z |
| format | Article |
| id | doaj.art-d8c7785e68204ad08cffbfb523afb0c4 |
| institution | Directory Open Access Journal |
| issn | 1999-4915 |
| language | English |
| last_indexed | 2024-03-10T23:31:07Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Viruses |
| spelling | doaj.art-d8c7785e68204ad08cffbfb523afb0c42023-11-19T03:21:16ZengMDPI AGViruses1999-49152023-08-01158174910.3390/v15081749Physics-Informed Neural Networks Integrating Compartmental Model for Analyzing COVID-19 Transmission DynamicsXiao Ning0Jinxing Guan1Xi-An Li2Yongyue Wei3Feng Chen4State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, 2 Sipailou, Nanjing 210096, ChinaCenter for Global Health, Departments of Epidemiology and Biostatistics, School of Public Health, Nanjing Medical University, Nanjing 211166, ChinaCeyear Technology Co., Ltd., 98 Xiangjiang Road, Qingdao 266000, ChinaCenter for Global Health, Departments of Epidemiology and Biostatistics, School of Public Health, Nanjing Medical University, Nanjing 211166, ChinaState Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, 2 Sipailou, Nanjing 210096, ChinaModelling and predicting the behaviour of infectious diseases is essential for early warning and evaluating the most effective interventions to prevent significant harm. Compartmental models produce a system of ordinary differential equations (ODEs) that are renowned for simulating the transmission dynamics of infectious diseases. However, the parameters in compartmental models are often unknown, and they can even change over time in the real world, making them difficult to determine. This study proposes an advanced artificial intelligence approach based on physics-informed neural networks (PINNs) to estimate time-varying parameters from given data for the compartmental model. Our proposed PINNs method captures the complex dynamics of COVID-19 by integrating a modified Susceptible-Exposed-Infectious-Recovered-Death (SEIRD) compartmental model with deep neural networks. Specifically, we modelled the system of ODEs as one network and the time-varying parameters as another network to address significant unknown parameters and limited data. Such structure of the PINNs method is in line with the prior epidemiological correlations and comprises the mismatch between available data and network output and the residual of ODEs. The experimental findings on real-world reported data data have demonstrated that our method robustly and accurately learns the dynamics and forecasts future states. Moreover, as more data becomes available, our proposed PINNs method can be successfully extended to other regions and infectious diseases.https://www.mdpi.com/1999-4915/15/8/1749compartmental modelsforward-inverse problemphysics-informed neural networksCOVID-19 transmission |
| spellingShingle | Xiao Ning Jinxing Guan Xi-An Li Yongyue Wei Feng Chen Physics-Informed Neural Networks Integrating Compartmental Model for Analyzing COVID-19 Transmission Dynamics Viruses compartmental models forward-inverse problem physics-informed neural networks COVID-19 transmission |
| title | Physics-Informed Neural Networks Integrating Compartmental Model for Analyzing COVID-19 Transmission Dynamics |
| title_full | Physics-Informed Neural Networks Integrating Compartmental Model for Analyzing COVID-19 Transmission Dynamics |
| title_fullStr | Physics-Informed Neural Networks Integrating Compartmental Model for Analyzing COVID-19 Transmission Dynamics |
| title_full_unstemmed | Physics-Informed Neural Networks Integrating Compartmental Model for Analyzing COVID-19 Transmission Dynamics |
| title_short | Physics-Informed Neural Networks Integrating Compartmental Model for Analyzing COVID-19 Transmission Dynamics |
| title_sort | physics informed neural networks integrating compartmental model for analyzing covid 19 transmission dynamics |
| topic | compartmental models forward-inverse problem physics-informed neural networks COVID-19 transmission |
| url | https://www.mdpi.com/1999-4915/15/8/1749 |
| work_keys_str_mv | AT xiaoning physicsinformedneuralnetworksintegratingcompartmentalmodelforanalyzingcovid19transmissiondynamics AT jinxingguan physicsinformedneuralnetworksintegratingcompartmentalmodelforanalyzingcovid19transmissiondynamics AT xianli physicsinformedneuralnetworksintegratingcompartmentalmodelforanalyzingcovid19transmissiondynamics AT yongyuewei physicsinformedneuralnetworksintegratingcompartmentalmodelforanalyzingcovid19transmissiondynamics AT fengchen physicsinformedneuralnetworksintegratingcompartmentalmodelforanalyzingcovid19transmissiondynamics |