Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Environmental Geosciences, Department of Geosciences, University of Oslo, P.O. Box 1047 Blindern, 0316 Oslo, Norway.
3
0
3
Surprisingly, deep ensembles *worsen* performance under physics constraints in PINNs for methane sorption, highlighting the importance of uncertainty quantification method selection in physics-informed machine learning.
Classical models of hydrogen storage in geological formations fall apart when applied to diverse samples, but this physics-informed neural network nails it, achieving R2 = 0.9544.
Predicting permeability tensors from microstructure images just got 33% more accurate thanks to a physics-informed CNN-Transformer that learns faster and generalizes better via pretraining and differentiable constraints.