Leveraging physics-informed neural networks for efficient modelling of coastal ecosystems dynamics: A case study of Sundarbans mangrove forest
Modelling the hydro-morphodynamics of mangrove environments poses significant challenges due to their complex geometry, dynamic vegetation-water interactions, and limited in situ measurements. Traditional numerical models struggle in such settings due to high computational cost, the need for extensi...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954125003115 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839629570454585344 |
|---|---|
| author | Majdi Fanous Jonathan M. Eden Juntao Yang Simon See Vasile Palade Alireza Daneshkhah |
| author_facet | Majdi Fanous Jonathan M. Eden Juntao Yang Simon See Vasile Palade Alireza Daneshkhah |
| author_sort | Majdi Fanous |
| collection | DOAJ |
| description | Modelling the hydro-morphodynamics of mangrove environments poses significant challenges due to their complex geometry, dynamic vegetation-water interactions, and limited in situ measurements. Traditional numerical models struggle in such settings due to high computational cost, the need for extensive mesh generation, and difficulties in assimilating heterogeneous data sources. To overcome these limitations, this study proposes a hybrid Physics-Informed Neural Networks (PINNs) framework that integrates governing physical laws, satellite-derived vegetation data, and outputs from high- resolution Computational Fluid Dynamics (CFD) simulations of the Sundarbans mangrove system. The proposed hybrid PINN model incorporates shallow water flow and sediment transport equations into the loss function and uses a temporal causality weighting mechanism to improve convergence in time-dependent domains. Model outputs include elevation, flow velocity, and suspended sediment concentration. The model is trained using a small subset of CFD simulation data and validated against a traditional finite element (FE) solver and a Convolutional Neural Network (CNN) baseline. The proposed hybrid PINNs model achieved RMSE values in the range of 10−2 for elevation and velocity and 10−3 for sediment concentration, significantly outperforming the CNN model, particularly in generalising to unseen time steps. Compared to the FE model, the proposed framework achieved a five-fold reduction in training time (24 h vs. 5 days) and supports inference within seconds, enabling near real-time predictions. The mesh-free structure of the model, combined with its physics-regularised learning, also facilitates adaptation to other coastal or mangrove systems governed by similar dynamics. This hybrid approach offers a robust, generalisable surrogate for high-fidelity coastal simulations in data-scarce and computationally demanding environments. |
| format | Article |
| id | doaj-art-092fd6b1b8464d25a8afbffd33bed93f |
| institution | Matheson Library |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-092fd6b1b8464d25a8afbffd33bed93f2025-07-15T04:16:00ZengElsevierEcological Informatics1574-95412025-12-0190103302Leveraging physics-informed neural networks for efficient modelling of coastal ecosystems dynamics: A case study of Sundarbans mangrove forestMajdi Fanous0Jonathan M. Eden1Juntao Yang2Simon See3Vasile Palade4Alireza Daneshkhah5Centre for Computational Science & Mathematical Modelling, Coventry University, Priory Street, Coventry, CV1 5FB, United KingdomCentre for Agroecology, Water and Resilience, Coventry University, Ryton Gardens, Wolston Lane, Warwickshire, CV8 3LG, United KingdomNVIDIA AI Technology Center, Temasek Blvd, Cityhall District, 038988, SingaporeCentre for Computational Science & Mathematical Modelling, Coventry University, Priory Street, Coventry, CV1 5FB, United Kingdom; NVIDIA AI Technology Center, San Tomas Expy, Santa Clara, 95051, United States of AmericaCentre for Computational Science & Mathematical Modelling, Coventry University, Priory Street, Coventry, CV1 5FB, United KingdomFaculty of Mathematics and Data Science, Emirates Aviation University, Dubai, P.O. Box 53044, United Arab Emirates; Corresponding author.Modelling the hydro-morphodynamics of mangrove environments poses significant challenges due to their complex geometry, dynamic vegetation-water interactions, and limited in situ measurements. Traditional numerical models struggle in such settings due to high computational cost, the need for extensive mesh generation, and difficulties in assimilating heterogeneous data sources. To overcome these limitations, this study proposes a hybrid Physics-Informed Neural Networks (PINNs) framework that integrates governing physical laws, satellite-derived vegetation data, and outputs from high- resolution Computational Fluid Dynamics (CFD) simulations of the Sundarbans mangrove system. The proposed hybrid PINN model incorporates shallow water flow and sediment transport equations into the loss function and uses a temporal causality weighting mechanism to improve convergence in time-dependent domains. Model outputs include elevation, flow velocity, and suspended sediment concentration. The model is trained using a small subset of CFD simulation data and validated against a traditional finite element (FE) solver and a Convolutional Neural Network (CNN) baseline. The proposed hybrid PINNs model achieved RMSE values in the range of 10−2 for elevation and velocity and 10−3 for sediment concentration, significantly outperforming the CNN model, particularly in generalising to unseen time steps. Compared to the FE model, the proposed framework achieved a five-fold reduction in training time (24 h vs. 5 days) and supports inference within seconds, enabling near real-time predictions. The mesh-free structure of the model, combined with its physics-regularised learning, also facilitates adaptation to other coastal or mangrove systems governed by similar dynamics. This hybrid approach offers a robust, generalisable surrogate for high-fidelity coastal simulations in data-scarce and computationally demanding environments.http://www.sciencedirect.com/science/article/pii/S1574954125003115Climate changeHybrid surrogate modellingHydrodynamic modellingMangrove dynamics simulationPhysics-informed neural networksSediment transport |
| spellingShingle | Majdi Fanous Jonathan M. Eden Juntao Yang Simon See Vasile Palade Alireza Daneshkhah Leveraging physics-informed neural networks for efficient modelling of coastal ecosystems dynamics: A case study of Sundarbans mangrove forest Ecological Informatics Climate change Hybrid surrogate modelling Hydrodynamic modelling Mangrove dynamics simulation Physics-informed neural networks Sediment transport |
| title | Leveraging physics-informed neural networks for efficient modelling of coastal ecosystems dynamics: A case study of Sundarbans mangrove forest |
| title_full | Leveraging physics-informed neural networks for efficient modelling of coastal ecosystems dynamics: A case study of Sundarbans mangrove forest |
| title_fullStr | Leveraging physics-informed neural networks for efficient modelling of coastal ecosystems dynamics: A case study of Sundarbans mangrove forest |
| title_full_unstemmed | Leveraging physics-informed neural networks for efficient modelling of coastal ecosystems dynamics: A case study of Sundarbans mangrove forest |
| title_short | Leveraging physics-informed neural networks for efficient modelling of coastal ecosystems dynamics: A case study of Sundarbans mangrove forest |
| title_sort | leveraging physics informed neural networks for efficient modelling of coastal ecosystems dynamics a case study of sundarbans mangrove forest |
| topic | Climate change Hybrid surrogate modelling Hydrodynamic modelling Mangrove dynamics simulation Physics-informed neural networks Sediment transport |
| url | http://www.sciencedirect.com/science/article/pii/S1574954125003115 |
| work_keys_str_mv | AT majdifanous leveragingphysicsinformedneuralnetworksforefficientmodellingofcoastalecosystemsdynamicsacasestudyofsundarbansmangroveforest AT jonathanmeden leveragingphysicsinformedneuralnetworksforefficientmodellingofcoastalecosystemsdynamicsacasestudyofsundarbansmangroveforest AT juntaoyang leveragingphysicsinformedneuralnetworksforefficientmodellingofcoastalecosystemsdynamicsacasestudyofsundarbansmangroveforest AT simonsee leveragingphysicsinformedneuralnetworksforefficientmodellingofcoastalecosystemsdynamicsacasestudyofsundarbansmangroveforest AT vasilepalade leveragingphysicsinformedneuralnetworksforefficientmodellingofcoastalecosystemsdynamicsacasestudyofsundarbansmangroveforest AT alirezadaneshkhah leveragingphysicsinformedneuralnetworksforefficientmodellingofcoastalecosystemsdynamicsacasestudyofsundarbansmangroveforest |