ICLRApr, 2021
提高城市气象污染预测的对抗自编码器和对抗 LSTM
Adversarial autoencoders and adversarial LSTM for improved forecasts of urban air pollution simulations
César Quilodrán-Casas, Rossella Arcucci, Laetitia Mottet, Yike Guo, Christopher Pain
TL;DR本文利用深度学习中的对抗训练方法,尤其是 PCA-based 对抗自编码器和 LSTM 网络的方法,提高了城市空气污染 CFD 模拟的预报精度。