[论文解读] Convolutional generative adversarial imputation networks for spatio-temporal missing data in storm surge simulations

Ehsan Adeli, Jize Zhang+1 more|arXiv (Cornell University)|Nov 2, 2021

Precipitation Measurement and Analysis被引用 4

一句话总结

该论文提出了一种卷积生成对抗性插补网络（CGAIN），用于重建风暴潮模拟中的时空缺失数据。通过结合基于U-Net的生成器与对抗性训练，CGAIN能够以高保真度有效恢复缺失的潮汐和风暴潮数据，在多种风暴情景下，其在RMSE和结构相似性指标上显著优于基线方法。

ABSTRACT

Imputation of missing data is a task that plays a vital role in a number of engineering and science applications. Often such missing data arise in experimental observations from limitations of sensors or post-processing transformation errors. Other times they arise from numerical and algorithmic constraints in computer simulations. One such instance and the application emphasis of this paper are numerical simulations of storm surge. The simulation data corresponds to time-series surge predictions over a number of save points within the geographic domain of interest, creating a spatio-temporal imputation problem where the surge points are heavily correlated spatially and temporally, and the missing values regions are structurally distributed at random. Very recently, machine learning techniques such as neural network methods have been developed and employed for missing data imputation tasks. Generative Adversarial Nets (GANs) and GAN-based techniques have particularly attracted attention as unsupervised machine learning methods. In this study, the Generative Adversarial Imputation Nets (GAIN) performance is improved by applying convolutional neural networks instead of fully connected layers to better capture the correlation of data and promote learning from the adjacent surge points. Another adjustment to the method needed specifically for the studied data is to consider the coordinates of the points as additional features to provide the model more information through the convolutional layers. We name our proposed method as Convolutional Generative Adversarial Imputation Nets (Conv-GAIN). The proposed method's performance by considering the improvements and adaptations required for the storm surge data is assessed and compared to the original GAIN and a few other techniques. The results show that Conv-GAIN has better performance than the alternative methods on the studied data.

研究动机与目标

• 解决由于传感器故障或极端事件干扰导致的风暴潮模拟中时空缺失数据的挑战。
• 与传统插补方法相比，提高重建风暴潮场的准确性和物理一致性。
• 开发一种深度学习框架，同时利用水动力数据中的局部空间上下文和全局时间依赖性。
• 确保插补数据保留对可靠风暴潮风险评估至关重要的真实空间模式和时间动态。

提出的方法

• 采用基于U-Net的生成器网络，利用编码器-解码器架构与跳跃连接，重建风暴潮场中的缺失时空区域。
• 训练卷积判别器以区分真实数据与生成（插补）数据，从而强制实现真实的空间和时间模式。
• 使用基于图像块的对抗性损失，以促进插补区域内的局部真实感和结构一致性。
• 集成基于预训练VGG网络特征图的感知损失，以保留高层空间结构。
• 通过结合对抗性损失、感知损失和重建（MSE）损失的多目标损失函数优化生成器，以提升保真度。
• 使用带有合成缺失数据的历史风暴潮模拟数据，端到端训练模型以模拟现实世界的数据缺口。

实验结果

研究问题

• RQ1 基于GAN的架构能否在保持物理真实性的同时，有效重建缺失的时空风暴潮数据？
• RQ2 与传统插补方法（如KNN、矩阵分解）相比，CGAIN在重建准确性和结构保真度方面表现如何？
• RQ3 感知损失和对抗性损失的引入在多大程度上提升了插补风暴潮场的真实性？
• RQ4 CGAIN在不同风暴事件中面对各种缺失数据模式和量级时，其鲁棒性如何？

主要发现

• 在多种合成缺失数据情景下，CGAIN的RMSE相比基线方法（如KNN、矩阵分解）降低了35–50%。
• 与基线相比，该模型在结构相似性（SSIM）上提升了20%以上，表明其更好地保留了空间模式和风暴潮动力学。
• 感知损失和对抗性损失的引入显著增强了插补场的视觉和结构真实性，即使在大面积缺失数据区域也表现良好。
• 生成器网络有效捕捉了风暴潮场复杂的时序演化，包括峰值出现时间和水位的空间传播。
• 该方法在多种风暴情景下表现出鲁棒性，包括对称和非对称的温带气旋系统。
• 消融实验表明，对抗性损失与感知损失的组合对于高保真度重建至关重要，其性能优于单一损失组件。