Interpretable and Explainable Surrogate Modeling for Simulations: A State-of-the-Art Survey and Perspectives on Explainable AI for Decision-Making

1. 1Apply surrogate modeling techniques to reduce computational costs in simulations
2. 2Use explainable AI methods to interpret surrogate models and understand input variable effects
3. 3Evaluate the performance of surrogate models using metrics such as accuracy and fidelity
4. 4Implement techniques to improve model transparency, such as feature attribution and model interpretability
5. 5Integrate explainable AI into the simulation workflow to support decision-making

Data scientists and researchers working on complex system simulations can benefit from this survey to improve model interpretability and explainability, enabling better decision-making

💡 Explainable AI can enhance the interpretability and transparency of surrogate models, leading to better decision-making in complex system simulations

🤖 Improve simulation-based decision-making with interpretable & explainable surrogate modeling! 💡