Mikhail Maslyaev
ABSTRACT
Evolutionary differential equation discovery proved to be a tool to obtain equations with less a priori assumptions than conventional approaches, such as sparse symbolic regression over the complete possible terms library. The equation discovery field contains two independent directions. The first one is purely mathematical and concerns differentiation, the object of optimization and its relation to the functional spaces and others. The second one is dedicated purely to the optimizatioal problem statement. Both topics are worth investigating to improve the algorithm's ability to handle experimental data a more artificial intelligence way, without significant pre-processing and a priori knowledge of their nature. In the paper, we consider the prevalence of either single-objective optimization, which considers only the discrepancy between selected terms in the equation, or multi-objective optimization, which additionally takes into account the complexity of the obtained equation. The proposed comparison approach is shown on classical model examples - Burgers equation, wave equation, and Korteweg - de Vries equation.
Supplemental Material
Available for Download
Supplemental material.
- H. Cao, L. Kang, Y. Chen, et al. 2000. Evolutionary Modeling of Systems of Ordinary Differential Equations with Genetic Programming. Genetic Programming and Evolvable Machines 1 (2000), 309--337. Google Scholar
Digital Library
- Urban Fasel, J Nathan Kutz, Bingni W Brunton, and Steven L Brunton. 2022. Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and control. Proceedings of the Royal Society A 478, 2260 (2022), 20210904.Google ScholarCross Ref
- Han Gao, Matthew J Zahr, and Jian-Xun Wang. 2022. Physics-informed graph neural galerkin networks: A unified framework for solving pde-governed forward and inverse problems. Computer Methods in Applied Mechanics and Engineering 390 (2022), 114502.Google ScholarCross Ref
- L Gao, Urban Fasel, Steven L Brunton, and J Nathan Kutz. 2023. Convergence of uncertainty estimates in Ensemble and Bayesian sparse model discovery. arXiv preprint arXiv:2301.12649 (2023).Google Scholar
- Hisao Ishibuchi, Yusuke Nojima, and Tsutomu Doi. 2006. Comparison between single-objective and multi-objective genetic algorithms: Performance comparison and performance measures. In 2006 IEEE International Conference on Evolutionary Computation. IEEE, 1143--1150.Google ScholarCross Ref
- Q. Zhang K. Li, K. Deb and S. Kwong. 2015. An Evolutionary Many-Objective Optimization Algorithm Based on Dominance and Decomposition. in IEEE Transactions on Evolutionary Computation) 19, 5 (2015), 694--716. Google ScholarDigital Library
- Lu Lu, Xuhui Meng, Zhiping Mao, and George Em Karniadakis. 2021. DeepXDE: A deep learning library for solving differential equations. SIAM Rev. 63, 1 (2021), 208--228.Google ScholarDigital Library
- Mikhail Maslyaev and Alexander Hvatov. 2021. Multi-Objective Discovery of PDE Systems Using Evolutionary Approach. In 2021 IEEE Congress on Evolutionary Computation (CEC). 596--603. Google ScholarDigital Library
- Mikhail Maslyaev and Alexander Hvatov. 2022. Solver-Based Fitness Function for the Data-Driven Evolutionary Discovery of Partial Differential Equations. In 2022 IEEE Congress on Evolutionary Computation (CEC). IEEE, 1--8.Google Scholar
- Mikhail Maslyaev, Alexander Hvatov, and Anna V Kalyuzhnaya. 2021. Partial differential equations discovery with EPDE framework: application for real and synthetic data. Journal of Computational Science (2021), 101345.Google Scholar
- Daniel A Messenger and David M Bortz. 2021. Weak SINDy for partial differential equations. J. Comput. Phys. 443 (2021), 110525.Google ScholarDigital Library
- Lizhen Nie and Veronika Ročková. 2022. Bayesian Bootstrap Spike-and-Slab LASSO. J. Amer. Statist. Assoc. 0, 0 (2022), 1--16. Google ScholarCross Ref
- M Raissi, P Perdikaris, and GE Karniadakis. 2017. Physics informed deep learning (Part II): Data-driven discovery of nonlinear partial differential equations. arXiv preprint arXiv:1711.10566 (2017). https://arxiv.org/abs/1711.10566Google Scholar
- Mikhail Sarafanov, Valerii Pokrovskii, and Nikolay O Nikitin. 2022. Evolutionary Automated Machine Learning for Multi-Scale Decomposition and Forecasting of Sensor Time Series. In 2022 IEEE Congress on Evolutionary Computation (CEC). IEEE, 01--08.Google Scholar
- Hayden Schaeffer. 2017. Learning partial differential equations via data discovery and sparse optimization. Proc. R. Soc. A 473, 2197 (2017), 20160446.Google ScholarCross Ref
- H. Schaeffer, R. Caflisch, C. D. Hauck, and S. Osher. 2017. Learning partial differential equations via data discovery and sparse optimization. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Science (2017). https://doi.org/473(2197):20160446Google Scholar
- Pongpisit Thanasutives, Takashi Morita, Masayuki Numao, and Ken ichi Fukui. 2023. Noise-aware physics-informed machine learning for robust PDE discovery. Machine Learning: Science and Technology 4, 1 (feb 2023), 015009. Google ScholarCross Ref
Index Terms
- Comparison of Single- and Multi- Objective Optimization Quality for Evolutionary Equation Discovery
Recommendations
Numerical solutions of linear and nonlinear singular perturbation problems
A new method is developed by detecting the boundary layer of the solution of a singular perturbation problem. On the non-boundary layer domain, the singular perturbation problem is dominated by the reduced equation which is solved with standard ...
Applications of the Tau Method to problems in mathematical modelling: A survey of recent applications of the Tau Method to problems in mathematical modelling
New formulations and recent theoretical developments have made it possible to apply the Tau Method to a variety of interesting problems of Engineering Science where a high accuracy is required of the solution. These include strongly nonlinear, stiff and ...
On a method of Bownds for solving Volterra integral equations
An initial-value method of Bownds for solving Volterra integral equations is reexamined using a variable-step integrator to solve the differential equations. It is shown that such equations may be easily solved to an accuracy ofO(10ź8), the error ...
Comments