Performance Benchmarking of Parallel Hyperparameter Tuning for Deep Learning Based Tornado Predictions
Performance Benchmarking of Parallel Hyperparameter Tuning for Deep Learning Based Tornado Predictions
复制标题
DOI：
10.1016/j.bdr.2021.100212
复制
发表时间：
2021-02-19
影响因子：
3.3
通讯作者：
Wang, Jianwu
中科院分区：
文献类型：
--
作者：
Basalyga, Jonathan N.;Barajas, Carlos A.;Wang, Jianwu
由于天气模拟的巨大复杂性，用目前的模型预测猛烈的风暴和危险的天气条件可能需要很长时间。机器学习有可能更快地对龙卷风天气模式进行分类，从而能够更及时地向公众发出警报。为了应对机器学习中的类不平衡挑战，人们提出了不同的数据增强方法。在这项工作中，我们检查了在基于卷积神经网络的龙卷风预测训练中，实时数据增强方法与使用预增强数据的墙体时间差。我们还比较了在不同大小的扩充数据集上基于CPU和GPU的训练。此外，我们还考察了在给定卷积神经网络的情况下，改变用于训练的GPU的数量会对墙的时间和精度产生什么影响。我们的结论是，使用多个GPU训练单个网络与使用单个GPU相比没有显著优势。训练期间使用的GPU数量应该尽可能少，以获得最大的搜索吞吐量，因为本地Kera多GPU模型在具有最佳学习参数的情况下提供的加速比很小。(C)2021 Elsevier Inc.保留所有权利。
Predicting violent storms and dangerous weather conditions with current models can take a long time due to the immense complexity associated with weather simulation. Machine learning has the potential to classify tornadic weather patterns much more rapidly, thus allowing for more timely alerts to the public. To deal with class imbalance challenges in machine learning, different data augmentation approaches have been proposed. In this work, we examine the wall time difference between live data augmentation methods versus the use of preaugmented data when they are used in a convolutional neural network based training for tornado prediction. We also compare CPU and GPU based training over varying sizes of augmented data sets. Additionally we examine what impact varying the number of GPUs used for training will produce given a convolutional neural network on wall time and accuracy. We conclude that using multiple GPUs to train a single network has no significant advantage over using a single GPU. The number of GPUs used during training should be kept as small as possible for maximum search throughput as the native Keras multi-GPU model provides little speedup with optimal learning parameters. (C) 2021 Elsevier Inc. All rights reserved.