# Physics-informed AI Accelerated Retention Analysis of Ferroelectric Vertical NAND: From Day-Scale TCAD to Second-Scale Surrogate Model

Source: [Physics-informed AI Accelerated Retention Analysis of Ferroelectric Vertical NAND: From Day-Scale TCAD to Second-Scale Surrogate Model](<https://www.sota2.com/research/paper/69afa5602d603e6de3e437e5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-29T05:00:05.003Z

Authors: Gyujun Jeong, Sungwon Cho, Minji Shon, Namhoon Kim, Woohyun Hwang, Kwangyou Seo, Suhwan Lim, Wanki Kim, Daewon Ha, Prasanna Venkatesan, Kihang Youn, Ram Cherukuri, Yiyi Wang, Suman Datta, Asif Khan, Shimeng Yu (1) \_\_INSTITUTION\_16\_\_ School of Electrical, Computer Engineering, Georgia Institute of Technology, GA, USA, (2) Semiconductor Research, Development, Samsung Electronics Co., Ltd, South Korea, (3) NVIDIA, Santa Clara, CA, USA)

Published: 2026-03-06T21:01:31.000Z

## Abstract

Ferroelectric field-effect transistors (FeFET)-based vertical NAND (Fe-VNAND) has emerged as a promising candidate to overcome z-scaling limitations with lower programming voltages. However, the data retention of 3D Fe-VNAND is hindered by the complex interaction between charge detrapping and ferroelectric depolarization. Developing optimized device designs requires exploring an extensive parameter space, but the high computational cost of conventional Technology Computer-Aided Design (TCAD) tools makes such wide-scale optimization impractical. To overcome these simulation barriers, we present a Physics-Informed Neural Operator (PINO)-based AI surrogate model designed for high-efficiency prediction of threshold voltage (Vth) shifts and retention behavior. By embedding fundamental physical principles into the learning architecture, our PINO framework achieves a speedup exceeding 10000x compared to TCAD while maintaining physical accuracy. The resulting surrogate provides a physics-consistent data engine for compact model parameter extraction and look-up-table (LUT) generation, directly supporting reliability-aware SPICE simulation of Fe-VNAND. This study demonstrates the model's effectiveness on a single FeFET configuration, serving as a pathway toward modeling the retention loss mechanisms.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Computational Efficiency on Fe-VNAND retention analysis simulation](<https://www.sota2.com/research/sota/computational-efficiency-on-fe-vnand-retention-analysis-simulation.md>): Computational Efficiency; Fe-VNAND retention analysis simulation; Single Sweep Simulation Time: 0.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.06881>)

[PDF](<https://arxiv.org/pdf/2603.06881.pdf>)
