Convolutional generative adversarial imputation networks for spatio-temporal missing data in storm surge simulations

TL;DR

This paper introduces Conv-GAIN, a convolutional neural network-based method that improves missing data imputation in spatio-temporal storm surge simulations, outperforming existing techniques.

Contribution

The paper proposes Conv-GAIN, a novel adaptation of GAIN using convolutional layers and coordinate features for better spatio-temporal data imputation.

Findings

Conv-GAIN outperforms original GAIN in storm surge data imputation.

Incorporating spatial and temporal correlations improves imputation accuracy.

Adding coordinate features enhances model performance.

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.