Skip to content
NewA calmer, faster ZeroHour

Physics-informed surrogate models one-dimensional p-n junction diodes

Original title: A physics-informed uncertainty-aware surrogate for $p$-$n$ junction diodes

arXiv cs.AI / cs.LG / cs.CLby Suchita Kulkarni ()1 min read1 · 1 read
AI summary · x-ai/grok-4.7Summaries by Vani AI

Median L1 error is 0.11% on potential and 1.5% and 0.61% on carrier densities.

The paper presents an uncertainty-aware physics-informed surrogate for a one-dimensional p-n junction diode, conditioned on device length, doping, and bias. Predicted internal state is used for terminal current, depletion width, peak field, and stored charge. Benchmarks indicate the formalism can extend to asymmetric junctions and two-dimensional diodes. An uncertainty analysis checks whether answers stay inside a user-specified tolerance.

Key facts
  • The reported surrogate targets a one-dimensional symmetric junction.
  • Quantities include terminal current, depletion width, peak field, and stored charge.
  • Median L1 error is 0.11% on electrostatic potential.
  • Electron and hole density median L1 errors are 1.5% and 0.61%.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at arxiv.org

We develop an uncertainty-aware physics-informed surrogate for a one-dimensional $p$-$n$ junction diode, conditioned on device length, doping and bias. Using the internal state of the device as predicted by the surrogate we develop a test-suite of quantities of interest including the terminal current, depletion width, peak field and stored charge.

arXiv cs.AI / cs.LG / cs.CL

By Suchita Kulkarni · arxiv.org

Read the full article at arXiv cs.AI / cs.LG / cs.CL

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.