Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications

Luna Gutierrez, Ricardo; Ghorbanpour, Sahand; Ejaz, Rahman; Gopalaswamy, Varchas; Betti, Riccardo; Gundecha, Vineet; Lees, Aarne; Sarkar, Soumyendu

doi:10.24963/ijcai.2026/815

Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications

Ricardo Luna Gutierrez, Sahand Ghorbanpour, Rahman Ejaz, Varchas Gopalaswamy, Riccardo Betti, Vineet Gundecha, Aarne Lees, Soumyendu Sarkar

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. AI and Social Good. Pages 7328-7336.

https://doi.org/10.24963/ijcai.2026/815

Keywords

Machine Learning: Machine Learning
Multidisciplinary Topics and Applications: Multidisciplinary Topics and Applications

Abstract

Inertial Confinement Fusion (ICF) holds transformative promise for sustainable, near-limitless clean energy, yet remains constrained by prohibitively high costs and limited experimental opportunities. This paper presents Human-in-the-Loop Meta Bayesian Optimization (HL-MBO), a framework that integrates expert knowledge with few-shot, uncertainty-aware machine learning to accelerate discovery in data-scarce, high-stakes scientific domains. HL-MBO introduces a meta-learned surrogate model with an expert-informed acquisition function to recommend candidate experiments. To foster trust and enable informed decisions, HL-MBO also provides interpretable explanations of its suggestions. We show that HL-MBO outperforms current BO methods for ICF energy yield optimization, as well as benchmarks in molecular optimization and critical-temperature maximization for superconducting materials.

Ricardo Luna Gutierrez, Sahand Ghorbanpour, Rahman Ejaz, Varchas Gopalaswamy, Riccardo Betti, Vineet Gundecha, Aarne Lees, and Soumyendu Sarkar. 2026. Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 7328–7336. https://doi.org/10.24963/ijcai.2026/815

@inproceedings{ijcai2026p815,
  title     = {Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications},
  author    = {Luna Gutierrez, Ricardo and Ghorbanpour, Sahand and Ejaz, Rahman and Gopalaswamy, Varchas and Betti, Riccardo and Gundecha, Vineet and Lees, Aarne and Sarkar, Soumyendu},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {7328--7336},
  year      = {2026},
  month     = {8},
  note      = {AI and Social Good},
  doi       = {10.24963/ijcai.2026/815},
  url       = {https://doi.org/10.24963/ijcai.2026/815},
}

TY  - CPAPER
TI  - Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications
AU  - Luna Gutierrez, Ricardo
AU  - Ghorbanpour, Sahand
AU  - Ejaz, Rahman
AU  - Gopalaswamy, Varchas
AU  - Betti, Riccardo
AU  - Gundecha, Vineet
AU  - Lees, Aarne
AU  - Sarkar, Soumyendu
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 7328
EP  - 7336
DO  - 10.24963/ijcai.2026/815
UR  - https://doi.org/10.24963/ijcai.2026/815
ER  -