skip to main content


Title: STORM-GAN: Spatio-Temporal Meta-GAN for Cross-City Estimation of Human Mobility Responses to COVID-19
Award ID(s):
2147195 1942680 1952085 2105133 2021871
NSF-PAR ID:
10400928
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
2022 IEEE International Conference on Data Mining (ICDM)
Page Range / eLocation ID:
1 to 10
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. GaN-on-GaN vertical diode is a promising device for next-generation power electronics. Its breakdown voltage (BV) is limited by edge termination designs such as guard rings. The design space of guard rings is huge and it is difficult to optimize manually. In this paper, we propose an effective inverse design strategy to co-optimize BV and (V F Q) −1 , where BV, V F , and Q are the breakdown voltage, forward voltage, and reserve capacitive charge of the diode, respectively. Using rapid Technology Computer-Aided-Design (TCAD) simulations, neural network (NN), and Pareto front generation, a GaN-on-GaN diode is optimized within 24 hours. We can obtain structures with 200V higher BV at medium (V F Q) −1 or find a nearly ideal BV structure with 25% higher BV 2 /R on compared to the best randomly generated TCAD data. 
    more » « less