# High-Dimensional Materials and Process Optimization using Data-driven Experimental Design with Well-Calibrated Uncertainty Estimates

arXiv: https://arxiv.org/abs/1704.07423 · HTML: https://mlsanity.com/paper/1704.07423/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2017.

## Built on by (most cited first, 14 of 14)

- [Computer-Aided Multi-Objective Optimization in Small Molecule Discovery](https://mlsanity.com/paper/2210.07209/) (2022)
- [LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs](https://mlsanity.com/paper/2605.24043/) (2026)
- [Interpretable models for extrapolation in scientific machine learning](https://mlsanity.com/paper/2212.10283/) (2022)
- [Uncertainty Prediction for Machine Learning Models of Material Properties](https://mlsanity.com/paper/2107.07997/) (2021)
- [Bayesian Optimization in Materials Science: A Survey](https://mlsanity.com/paper/2108.00002/) (2021)
- [Machine Learning with Knowledge Constraints for Process Optimization of Open-Air Perovskite Solar Cell Manufacturing](https://mlsanity.com/paper/2110.01387/) (2021)
- [Uncertainty-Aware Mixed-Variable Machine Learning for Materials Design](https://mlsanity.com/paper/2207.04994/) (2022)
- [A General Approach for Determining Applicability Domain of Machine Learning Models](https://mlsanity.com/paper/2406.05143/) (2024)
- [Accurate and Uncertainty-Aware Multi-Task Prediction of HEA Properties Using Prior-Guided Deep Gaussian Processes](https://mlsanity.com/paper/2506.14828/) (2025)
- [Multivariate Prediction Intervals for Random Forests](https://mlsanity.com/paper/2205.02260/) (2022)
- [Robustness in Fatigue Strength Estimation](https://mlsanity.com/paper/2212.01136/) (2022)
- [Materials Informatics: An Algorithmic Design Rule](https://mlsanity.com/paper/2305.03797/) (2023)
- [RAG: A Random-Forest-Based Generative Design Framework for Uncertainty-Aware Design of Metamaterials with Complex Functional Response Requirements](https://mlsanity.com/paper/2601.13233/) (2026)
- [AI-Guided Design and Optimization of Graphite-Based Anodes via Iterative Experimental Feedback](https://mlsanity.com/paper/2606.00187/) (2026)

## Abstract (arXiv)

The optimization of composition and processing to obtain materials that exhibit desirable characteristics has historically relied on a combination of scientist intuition, trial and error, and luck. We propose a methodology that can accelerate this process by fitting data-driven models to experimental data as it is collected to suggest which experiment should be performed next. This methodology can guide the scientist to test the most promising candidates earlier, and can supplement scientific intuition and knowledge with data-driven insights. A key strength of the proposed framework is that it scales to high-dimensional parameter spaces, as are typical in materials discovery applications. Importantly, the data-driven models incorporate uncertainty analysis, so that new experiments are proposed based on a combination of exploring high-uncertainty candidates and exploiting high-performing regions of parameter space. Over four materials science test cases, our methodology led to the optimal candidate being found with three times fewer required measurements than random guessing on average.