GPLFR is a Gaussian process model that analytically marginalizes decoder weights to couple latent factor compression with prediction for high-dimensional low-data regression, demonstrated via the first spatially resolved emulator of rocky exoplanet global climate models.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Different UV spectra for TRAPPIST-1 produce order-of-magnitude variations in CH4, CO, O2, and O3 abundances for Archean-analog TRAPPIST-1 e atmospheres, generating photochemical degeneracies and potential false-positive biosignatures.
citing papers explorer
-
Gaussian Process Latent Factor Regression for Low-Data, High-Dimensional Output Problems
GPLFR is a Gaussian process model that analytically marginalizes decoder weights to couple latent factor compression with prediction for high-dimensional low-data regression, demonstrated via the first spatially resolved emulator of rocky exoplanet global climate models.