A CNN trained on surrogate fuel spectra with pseudo-labeling, synthetic blending, and consistency augmentation predicts RON, MON, and DCN of real fuels from ATR-FTIR spectra with 23.9% lower MAE than a baseline CNN.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
physics.chem-ph 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Fuelprop: Fuel property prediction from ATR-FTIR spectroscopic data
A CNN trained on surrogate fuel spectra with pseudo-labeling, synthetic blending, and consistency augmentation predicts RON, MON, and DCN of real fuels from ATR-FTIR spectra with 23.9% lower MAE than a baseline CNN.