# Enhancing Multi-Objective Optimization through Machine Learning-Supported Multiphysics Simulation

arXiv: https://arxiv.org/abs/2309.13179 · HTML: https://mlsanity.com/paper/2309.13179/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 37 references that are in the map.
- First posted on arXiv 22 Sep 2023.

## Builds on (most cited first, 8 of 8)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks](https://mlsanity.com/paper/1905.13166/) (2019)
- [Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge](https://mlsanity.com/paper/1711.07970/) (2017)
- [Multi-Objective Quality Diversity Optimization](https://mlsanity.com/paper/2202.03057/) (2022)
- [Variational Autoencoder based Metamodeling for Multi-Objective Topology Optimization of Electrical Machines](https://mlsanity.com/paper/2201.08877/) (2022)
- [Dataset of a parameterized U-bend flow for Deep Learning Applications](https://mlsanity.com/paper/2305.05216/) (2023)
- [DADO -- Low-Cost Query Strategies for Deep Active Design Optimization](https://mlsanity.com/paper/2307.04536/) (2023)

## Built on by (most cited first, 2 of 2)

- [Multiscale Neural Operators for Solving Time-Independent PDEs](https://mlsanity.com/paper/2311.05964/) (2023)
- [From Structured to Unstructured:A Comparative Analysis of Computer Vision and Graph Models in solving Mesh-based PDEs](https://mlsanity.com/paper/2406.00081/) (2024)

## Abstract (arXiv)

This paper presents a methodological framework for training, self-optimising, and self-organising surrogate models to approximate and speed up multiobjective optimisation of technical systems based on multiphysics simulations. At the hand of two real-world datasets, we illustrate that surrogate models can be trained on relatively small amounts of data to approximate the underlying simulations accurately. Including explainable AI techniques allow for highlighting feature relevancy or dependencies and supporting the possible extension of the used datasets. One of the datasets was created for this paper and is made publicly available for the broader scientific community. Extensive experiments combine four machine learning and deep learning algorithms with an evolutionary optimisation algorithm. The performance of the combined training and optimisation pipeline is evaluated by verifying the generated Pareto-optimal results using the ground truth simulations. The results from our pipeline and a comprehensive evaluation strategy show the potential for efficiently acquiring solution candidates in multiobjective optimisation tasks by reducing the number of simulations and conserving a higher prediction accuracy, i.e., with a MAPE score under 5% for one of the presented use cases.