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

2026-03-06

AI Summary

This work addresses the challenge of modeling data retention in 3D ferroelectric vertical NAND, where charge detrapping and ferroelectric depolarization interact in a coupled manner, rendering traditional TCAD simulations computationally prohibitive for large-scale design optimization. To overcome this limitation, the study introduces, for the first time, the physics-informed neural operator (PINO) framework into ferroelectric memory modeling. A deep learning surrogate model is developed that embeds physical constraints and is trained on TCAD-generated data to accurately predict FeFET threshold voltage drift and data retention behavior. The proposed approach achieves over four orders of magnitude acceleration in simulation speed for individual devices while preserving physical accuracy comparable to TCAD, thereby offering a high-fidelity, highly efficient analysis tool for the design of 3D ferroelectric memory architectures.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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. This study demonstrates the model's effectiveness on a single FeFET configuration, serving as a pathway toward modeling the retention loss mechanisms.

Problem

• ferroelectric memory
• data retention
• TCAD simulation
• parameter optimization
• 3D Fe-VNAND

Innovation

• Physics-Informed Neural Operator
• Ferroelectric VNAND
• Retention Modeling
• AI Surrogate Model
• TCAD Acceleration