Aims and Scope

Evolutionary computation (EC) and physics-informed approaches have emerged as powerful paradigms for solving complex optimization and modeling challenges across scientific and engineering domains. While EC excels at exploring large solution spaces through population-based search, physics-informed methods incorporate domain knowledge to ensure solutions adhere to fundamental physical principles.

Key Focus Areas: The integration of these approaches presents exciting opportunities to overcome limitations in both fields: EC can benefit from physical constraints to guide more efficient searches, while physics-based models can leverage EC's global optimization capabilities to escape local optima and discover novel solutions.

This special issue explores the bidirectional synergy between these paradigms, where physical knowledge enhances EC optimization while EC methods advance physics-based modeling. We seek contributions that:

  • Develop novel physics-guided EC techniques with embedded domain knowledge through constrained operators and fitness functions
  • Employ EC to optimize physics-informed neural networks (PINNs) through architecture search, hyperparameter tuning, and multi-objective balancing
  • Demonstrate real-world applications where this integration yields more efficient, accurate, and interpretable solutions

Research Topics

🔬 Theoretical Foundations

  • Convergence analysis and stability properties
  • Mathematical frameworks for physics-guided operators
  • Physical constraint handling in evolutionary optimization

🧬 Physics-Enhanced EC Methods

  • Novel evolutionary operators with conservation laws
  • Physics-guided diversity maintenance strategies
  • Multi-objective approaches balancing constraints

🧠 EC for Physics-Informed Neural Networks

  • Evolutionary architecture search for PINNs
  • Coevolutionary optimization approaches
  • Population-based training strategies

âš¡ Computational Advances

  • Parallel and distributed algorithms
  • Physics-guided surrogate models
  • Adaptive evolutionary strategies

🚀 Real-World Applications

  • Engineering design optimization
  • Scientific computing and simulation
  • Complex physical system design

Related Publications

Recent advances in physics-informed evolutionary computation have been documented in various publications. Here are some references that demonstrate the growing interest and potential in this field:

Evolvable Conditional Diffusion
Zhao Wei, Chin Chun Ooi, Abhishek Gupta, Jian Cheng Wong, Pao-Hsiung Chiu, Sheares Xue Wen Toh, Yew-Soon Ong
In International Joint Conferences on Artificial Intelligence(IJCAI), 2025. 📄 PDF
Physics-informed neuro-evolution (PINE): A survey and prospects
Jian Cheng Wong, Abhishek Gupta, Chin Chun Ooi, Pao-Hsiung Chiu, Jiao Liu, and Yew-Soon Ong
arXiv preprint arXiv:2501.06572, 2025. 📄 PDF
Looks great, functions better: Physics compliance text-to-3D shape generation
Qingshan Xu, Jiao Liu, Melvin Wong, Caishun Chen, and Yew-Soon Ong
In International Joint Conference on Neural Networks (IJCNN), 2025. 📄 PDF
Towards end-to-end prompt-vision-physics neural network for fast design discovery
Qingshan Xu, Jiao Liu, Melvin Wong, Ge Jin, Ryan Lau, Yew-Soon Ong, Stefan Menzel, Thiago Rios, Joo-Hwee Lim, and Chin Chun Ooi
In IEEE Conference on Artificial Intelligence (CAI), pp. 1432-1435, 2024. 📄 Link
Fourier warm start for physics-informed neural networks
Ge Jin, Jian Cheng Wong, Abhishek Gupta, Shipeng Li, and Yew-Soon Ong
Engineering Applications of Artificial Intelligence, 132: 107887, 2024. 📄 Link
The Baldwin Effect in Advancing Generalizability of Physics-Informed Neural Networks
Jian Cheng Wong, Chin Chun Ooi, Abhishek Gupta, Pao-Hsiung Chiu, Joshua Shao Zheng Low, My Ha Dao, and Yew-Soon Ong
arXiv e-prints:arXiv-2312, 2023. 📄 PDF
Neuroevolution of physics-informed neural nets: Benchmark problems and comparative results
Nicholas Wei Yong Sung, Jian Cheng Wong, Chin Chun Ooi, Abhishek Gupta, Pao-Hsiung Chiu, and Yew-Soon Ong
In Proceedings of the Companion Conference on Genetic and Evolutionary Computation (GECCO), pp. 2144-2151, 2023. 📄 PDF
LSA-PINN: Linear boundary connectivity loss for solving PDEs on complex geometry
Jian Cheng Wong, Pao-Hsiung Chiu, Chin Chun Ooi, My Ha Dao, and Yew-Soon Ong
International Joint Conference on Neural Networks (IJCNN), pp. 1-10, 2023. 📄 PDF
How to select physics-informed neural networks in the absence of ground truth: A pareto front-based strategy
Zhao Wei, Jian Cheng Wong, Nicholas Wei Yong Sung, Abhishek Gupta, Chin Chun Ooi, Pao-Hsiung Chiu, My Ha Dao, and Yew-Soon Ong
1st Workshop on the Synergy of Scientific and Machine Learning Modeling@ICML, 2023. 📄 PDF
Learning in sinusoidal spaces with physics-informed neural networks
Jian Cheng Wong, Chin Chun Ooi, Abhishek Gupta, and Yew-Soon Ong
IEEE Transactions on Artificial Intelligence, 5(3): 985-1000, 2022. 📄 PDF
CAN-PINN: A fast physics-informed neural network based on coupled-automatic-numerical differentiation method
Pao-Hsiung Chiu, Jian Cheng Wong, Chin Chun Ooi, My Ha Dao, and Yew-Soon Ong
Computer Methods in Applied Mechanics and Engineering, 395: 114909, 2022. 📄 Link
Jax-accelerated neuroevolution of physics-informed neural networks: Benchmarks and experimental results
Nicholas Wei Yong Sung, Jian Cheng Wong, Pao-Hsiung Chiu, Abhishek Gupta, Chin Chun Ooi, and Yew-Soon Ong
arXiv preprint arXiv:2212.07624, 2022. 📄 Link
Can transfer neuroevolution tractably solve your differential equations?
Jian Cheng Wong, Abhishek Gupta, and Yew-Soon Ong
IEEE Computational Intelligence Magazine, 16(2): 14-30, 2021. 📄 PDF
... and more recent publications demonstrating the evolution of this field

Note: These publications showcase the diverse applications and methodological advances in physics-informed evolutionary computation, highlighting the potential for novel contributions in this emerging field.

Submission Guidelines

Manuscripts should be prepared according to the IEEE TEVC submission guidelines. Please ensure your submission represents original, unpublished work that is not under consideration elsewhere.

Submission Instructions:
• Follow guidelines at: IEEE TEVC Submission Portal
• Select article type as "PIEC"
• Add "Special Issue: Physics-Informed Evolutionary Computation: Advances and Applications" to Editor-in-Chief comments
🚀 Submit Your Paper