Physics-informed sparse modeling for GaN devices

SparseMind and MRDI are studying sparse surrogate models for GaN device simulation. The program covers GaN HEMTs and PIN diodes and uses physics-informed neural networks (PINNs) to incorporate physical constraints and reference data into training.

Method

Evaluate the accuracy, robustness and computational requirements of sparse surrogate models across device geometries and operating conditions, using TCAD results as the reference.

Acceptance targets

Targets include threshold-voltage error below 3%, dynamic on-resistance error below 5% and peak junction-temperature mean absolute error below 3°C. Subject to the voltage and resistance constraints, the model targets at least 60% sparsity, with at least 80% as a stretch target.

Next steps

The research aims for 1.5–2× speedup and millisecond-scale surrogate predictions. Accuracy, sparsity, speed and latency remain to be validated on the target hardware, data and workload.