Provider: Silverchair
Database: AmericanChemicalSociety
Content: text/plain; charset="UTF-8"

TY  - JOUR
AU  - Dong, Lechen
AU  - Liu, Fang
T1  - Early Detection
and Recovery of SCF Convergence Failures
in Automated Quantum Chemistry Workflows via Time-Series Learning
PY  - 2026
Y1  - 2026/08/25
DO  - 10.1021/acs.jctc.6c00928
JO  - Journal of Chemical Theory and Computation
JA  - J. Chem. Theory Comput.
SN  - 1549-9618
AB  - Self-consistent field
(SCF) convergence failures represent a major
bottleneck in high-throughput workflows, particularly for open-shell
systems and material discovery. To address this challenge, we introduce
an autonomous pipeline that treats the electronic structure descriptors
from early spin-unrestricted SCF iterations as a time-series problem.
Using statistical descriptors extracted from only ten iterations,
a lightweight gradient-boosted classifier accurately predicts convergence
failures. The model achieves 94.8% accuracy on 55,000 doublet anionic
QM9 test molecules after being trained on only 10,000 examples. We
then couple this early warning predictor with restart-based level-shifting
interventions derived from Bayesian optimization of the α- and
β-shifting parameters. Across six diverse SCF test sets, our
pipeline successfully rescued 53.9% of inherently difficult-to-converge
molecules while maintaining a 96.3% convergence rate for easy-to-converge
cases, reducing the total number of iterations across the 1,200 calculations
by 248,355 steps. Overall, this proof-of-concept demonstrates that
treating early SCF iterations as a time-series problem provides a
data-efficient active-monitoring layer, which can be paired with various
remedies to fine-tune convergence parameters and enable more autonomous,
large-scale electronic structure workflows.
Y2  - 8/25/2026
UR  - https://doi.org/10.1021/acs.jctc.6c00928
ER  -