SCALE: Simulation-Calibrated Amortized Learning for Energy Materials (A hybrid architecture connecting deterministic modeling, real-world data, and transformer-scale inference for accelerated energy-materials discovery)
Abstract
Energy systems face converging pressures for security, affordability, resilience, and sustainability, creating a need for faster discovery of deployable energy materials. Here we introduce SCALE (Simulation-Calibrated Amortized Learning for Energy Materials), a physics-grounded, real-world-data-calibrated learning architecture that connects deterministic scientific operators, experimental calibration, expanded calibrated label generation, and transformer-scale inference. SCALE converts selected high-cost mechanistic computation and measured evidence into reusable models for rapid screening, ranking, inverse design, and active learning. We formulate the framework, identify ten method-based application regimes, and demonstrate SCALE for solid-state metal-hydride hydrogen-storage capacity prediction. In this implementation, a hydride phase-equilibrium capacity operator is calibrated against 381 measured ML-HydPARK capacity anchors and used to generate 5,000 candidate-condition-prototype teacher labels. A crystallographically anchored periodic-graph representation preserves atomic sites, periodic neighbor relationships, and local metal environments absent from formula-only encodings. An edge-biased graph transformer with 2.90 million parameters reproduces calibrated teacher labels with five-fold surrogate fidelity of MAE 0.0582 wt% H2, RMSE 0.0833 wt% H2, R2 = 0.9927, and Pearson r = 0.9963. Post hoc attention analysis suggests that SCALE learns chemically organized element groupings and metal-metal relationships consistent with established hydride chemistry, without chemistry-group labels as supervision. Once trained, SCALE shifts million-candidate evaluation from repeated deterministic workflow execution to batched learned inference, reducing per-candidate screening cost by approximately 10^7-10^8 while retaining links to simulation and experimental evidence.
Related
- Acquisition-calibrated degradation synthesis and dual-domain reconstruction for accelerated spectral-domain OCT
- A Transformer model for precessing binary black-hole merger waveforms calibrated to numerical relativity
- Direct Neutrino Communication Through the Earth: NuMI-Calibrated Simulation and Far-Field Sensitivity
- Passage of particles through matter and the effective straggling-function: High-fidelity accelerated simulation via Physics-Informed Machine Learning
- Assessing the consistency of the CPL dark-energy model with cosmological data: Simulation-calibrated neural posterior disagreement
BibTeX
@misc{huang2026scale,
title = {{SCALE: Simulation-Calibrated Amortized Learning for Energy Materials (A hybrid architecture connecting deterministic modeling, real-world data, and transformer-scale inference for accelerated energy-materials discovery)}},
author = {Kuan Huang and Bo Bai},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.22233},
eprint = {2609.22233},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.22233},
}
RIS
TY - UNPB
TI - SCALE: Simulation-Calibrated Amortized Learning for Energy Materials (A hybrid architecture connecting deterministic modeling, real-world data, and transformer-scale inference for accelerated energy-materials discovery)
AU - Kuan Huang
AU - Bo Bai
PY - 2026
DA - 2026/09/03
PB - arXiv
DO - 10.48550/arxiv.2609.22233
UR - https://arxiv.org/abs/2609.22233
AB - Energy systems face converging pressures for security, affordability, resilience, and sustainability, creating a need for faster discovery of deployable energy materials. Here we introduce SCALE (Simulation-Calibrated Amortized Learning for Energy Materials), a physics-grounded, real-world-data-calibrated learning architecture that connects deterministic scientific operators, experimental calibration, expanded calibrated label generation, and transformer-scale inference. SCALE converts selected high-cost mechanistic computation and measured evidence into reusable models for rapid screening, ranking, inverse design, and active learning. We formulate the framework, identify ten method-based application regimes, and demonstrate SCALE for solid-state metal-hydride hydrogen-storage capacity prediction. In this implementation, a hydride phase-equilibrium capacity operator is calibrated against 381 measured ML-HydPARK capacity anchors and used to generate 5,000 candidate-condition-prototype teacher labels. A crystallographically anchored periodic-graph representation preserves atomic sites, periodic neighbor relationships, and local metal environments absent from formula-only encodings. An edge-biased graph transformer with 2.90 million parameters reproduces calibrated teacher labels with five-fold surrogate fidelity of MAE 0.0582 wt% H2, RMSE 0.0833 wt% H2, R2 = 0.9927, and Pearson r = 0.9963. Post hoc attention analysis suggests that SCALE learns chemically organized element groupings and metal-metal relationships consistent with established hydride chemistry, without chemistry-group labels as supervision. Once trained, SCALE shifts million-candidate evaluation from repeated deterministic workflow execution to batched learned inference, reducing per-candidate screening cost by approximately 10^7-10^8 while retaining links to simulation and experimental evidence.
ER -