SinoGreenTech Academic Portal
Official PDF TranslationSCIENCE CHINA Materials

Deep Learning-Driven Intelligent Prediction for Tailoring Electrical Properties of N2200-Based Donor-Acceptor Conjugated Copolymer OFETs

Authors: Jie Wu; Xuqi Yang; Jing Chen; Yufan Mao; Walid Boukhili; Guangyao Chen; Yuxuan Bao; Lei Wang

DOI: 10.1007/s40843-025-3701-1Status: Verified Translated Edition
Sponsored AdvertisementAd Placement Area
reCAPTCHA Bot Shield Active

Preparing Secure Academic Download

Verifying human reader & generating high-resolution document...

Verifying Document Integrity15s remaining
← Back to Article
Protected by Google reCAPTCHA v3.PrivacyTerms
Sponsored ContentAdSense In-Feed Ad Slot

Key Findings in This Report

• • Channel length reduction to 150 μm increased current density while maintaining leakage control, directly impacting device miniaturization and power efficiency in flexible electronics. • • Optimal N2200/PMMA concentration ratio of 7/100 mg/mL and annealing at 80 °C for 3 h improved crystallinity and interfacial properties, yielding stable electrical performance with reduced variability. • • CNN-PSO-BP hybrid model reduced MAE and RMSE by 15.7% and 14.9% for Vth, 10% and 9% for lg(Ion/Ioff), and 13.5% and 9.5% for SS compared to standard CNN, enhancing prediction accuracy for critical OFET parameters. • • The CNN model achieved R² > 0.9 for all metrics (R² Vth = 0.95, R² SS = 0.96), demonstrating superior predictive capability over BPNN and RF, and enabling reliable high-throughput virtual screening of OFET fabrication parameters.