Long-Term Missing Value Imputation for Time Series Data Using Deep Neural Networks
This addresses a common issue in long-term environmental monitoring where large gaps in data can hinder analysis, though it is incremental as it applies an existing deep learning method to a specific gap-filling task.
The paper tackled the problem of imputing long continuous gaps (e.g., months to years) in multivariate time series data, such as environmental monitoring datasets, by using a deep learning model (MLP) and found that it outperformed widely-used R-based methods like ImputeTS and mtsdi, especially for nonlinear data.
We present an approach that uses a deep learning model, in particular, a MultiLayer Perceptron (MLP), 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.