D. Hirmas

Efficient Emulation, Uncertainty Quantification, and Sensitivity Analysis for a Land Surface Model Using Evidential Deep Learning

Training an evidential deep neural network emulator on a 500‐member CLM5 perturbed parameter ensemble generated via Latin hypercube sampling of 32 key plant physiological parameters captures seasonal cycles, interannual variability in LAI, and uncertainties in a single pass, yielding well‐calibrated probabilistic outpu...