2 papers
cs.LG2026
PhyRestore: Physics-Structured Latent-Factor Restoration
Ahmed Shafee, Chayan Lahiri
Estimating temporal soil-loss change is challenging when physically meaningful input factors are noisy or corrupted, particularly because substantial changes are rare relative to t…
cs.LG2026
When Proxy Prediction Becomes Equation Reconstruction: Diagnostics and Residual Learning for Factor-Derived Proxy Supervision
Chayan Lahiri, Ahmed Shafee, Cody Fehringer
Scientific machine learning often relies on proxy targets computed from known domain factors when direct observations are limited. When those same factors are used as model inputs,…