4.6 Article

Long-term missing value imputation for time series data using deep neural networks

期刊

NEURAL COMPUTING & APPLICATIONS
卷 35, 期 12, 页码 9071-9091

出版社

SPRINGER LONDON LTD
DOI: 10.1007/s00521-022-08165-6

关键词

Missing value imputation; Environmental data; Machine learning; Hyperparameter optimization; Derivative-free optimization; Surrogate models

向作者/读者索取更多资源

We propose a deep learning model, specifically a MultiLayer Perceptron, for estimating missing values in multivariate time series data. Our algorithm focuses on filling long continuous gaps in the data and uses an automated method to determine the optimal MLP model architecture. We compared our approach to existing R-based methods and found that using an MLP leads to better results, particularly for nonlinear data.
We present an approach that uses a deep learning model, in particular, a MultiLayer Perceptron, for estimating the missing values of a variable in multivariate time series data. We focus on filling a long continuous gap (e.g., multiple months of missing daily observations) rather than on individual randomly missing observations. Our proposed gap filling algorithm uses an automated method for determining the optimal MLP model architecture, thus allowing for optimal prediction performance for the given time series. We tested our approach by filling gaps of various lengths (three months to three years) in three environmental datasets with different time series characteristics, namely daily groundwater levels, daily soil moisture, and hourly Net Ecosystem Exchange. We compared the accuracy of the gap-filled values obtained with our approach to the widely used R-based time series gap filling methods ImputeTS and mtsdi. The results indicate that using an MLP for filling a large gap leads to better results, especially when the data behave nonlinearly. Thus, our approach enables the use of datasets that have a large gap in one variable, which is common in many long-term environmental monitoring observations.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据