Empirical benchmarks show PINNs and operator networks are orders of magnitude slower and less accurate than finite-difference methods outside training intervals, while automatic differentiation through a conventional solver recovers material properties with ~1% error in seconds.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.geo-ph 1years
2025 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
A Critical Assessment of PINNs and Operator Learning for Geotechnical Engineering
Empirical benchmarks show PINNs and operator networks are orders of magnitude slower and less accurate than finite-difference methods outside training intervals, while automatic differentiation through a conventional solver recovers material properties with ~1% error in seconds.